🚨(backend) fix tests

I am removing hard coded datetime.

.gitignore

@@ -44,6 +44,9 @@ env.d/development/*
 !env.d/development/*.dist
 env.d/terraform
 
+# Configuration
+**/conversations/configuration/llm/dev.json
+
 # npm
 node_modules
 

CHANGELOG.md

@@ -8,15 +8,31 @@ and this project adheres to
 
 ## [Unreleased]
 
+### Added
+
+- ✨(backend) add FindRagBackend
+
+### Removed
+
+- 🔥(chat) consider PDF documents as other kind of documents #234
+
+## [0.0.11] - 2026-01-16
+
 ### Changed
 
 - 📦️(front) update react
+- ✨(chat) Generate and edit conversation title
 
 ### Fixed
 
 - 🐛(e2e) fix test-e2e-chromium
 - 🐛(back) fix system prompt compatibility with self-hosted models #200
 - ⚰️(back) remove dead code and unused files
+- 🐛(back) prevent tool call timeouts
+
+### Removed
+
+- 🔥(chat) remove thinking part from frontend #227
 
 ## [0.0.10] - 2025-12-15
 
@@ -172,7 +188,8 @@ and this project adheres to
 - 💄(chat) add code highlighting for LLM responses #67
 
 
-[unreleased]: https://github.com/suitenumerique/conversations/compare/v0.0.10...main
+[unreleased]: https://github.com/suitenumerique/conversations/compare/v0.0.11...main
+[0.0.11]: https://github.com/suitenumerique/conversations/releases/v0.0.11
 [0.0.10]: https://github.com/suitenumerique/conversations/releases/v0.0.10
 [0.0.9]: https://github.com/suitenumerique/conversations/releases/v0.0.9
 [0.0.8]: https://github.com/suitenumerique/conversations/releases/v0.0.8

Dockerfile

@@ -4,7 +4,7 @@
 FROM python:3.13.3-alpine AS base
 
 # Upgrade pip to its latest release to speed up dependencies installation
-RUN python -m pip install --upgrade pip setuptools
+RUN python -m pip install --upgrade pip
 
 # Upgrade system packages to install security updates
 RUN apk update && \

compose.yml

@@ -71,6 +71,9 @@ services:
       - "host.docker.internal:host-gateway"
     ports:
       - "8071:8000"
+    networks:
+      - default
+      - lasuite
     volumes:
       - ./src/backend:/app
       - ./data/static:/data/static
@@ -89,6 +92,9 @@ services:
     image: nginx:1.25
     ports:
       - "8083:8083"
+    networks:
+      - default
+      - lasuite
     volumes:
       - ./docker/files/etc/nginx/conf.d:/etc/nginx/conf.d:ro
     depends_on:
@@ -177,3 +183,8 @@ services:
       kc_postgresql:
         condition: service_healthy
         restart: true
+
+networks:
+  lasuite:
+    name: lasuite-network
+    driver: bridge

docs/env.md

@@ -95,6 +95,9 @@ These are the environment variables you can set for the `conversations-backend`
 | CACHES_KEY_PREFIX                               | The prefix used to every cache keys.                                                                                              | conversations                                           |
 | THEME_CUSTOMIZATION_FILE_PATH                   | full path to the file customizing the theme. An example is provided in src/backend/conversations/configuration/theme/default.json | BASE_DIR/conversations/configuration/theme/default.json |
 | THEME_CUSTOMIZATION_CACHE_TIMEOUT               | Cache duration for the customization settings                                                                                     | 86400                                                   |
+| FIND_API_KEY                                    | API key of Find                                                                                                                   |                                                         |
+| FIND_API_URL                                    | URL of Find                                                                                                                       | `https://app-find/api`                                  |
+| FIND_API_TIMEOUT                                | Find API timeout                                                                                                                  | 30                                                      |
 
 
 ## conversations-frontend image

docs/llm-configuration.md

@@ -244,9 +244,9 @@ For Mistral AI models using the Etalab platform:
 {
   "models": [
     {
-      "hrid": "mistral-large",
-      "model_name": "mistral-large-latest",
-      "human_readable_name": "Mistral Large (Etalab)",
+      "hrid": "mistral-medium",
+      "model_name": "mistral-medium-2508",
+      "human_readable_name": "Mistral Medium (Etalab)",
       "provider_name": "mistral-etalab",
       "profile": null,
       "settings": {

docs/tools/web_search_brave.md

@@ -357,6 +357,7 @@ The RAG backend performs semantic search to find the most relevant content:
 rag_results = document_store.search(
     query,
     results_count=settings.BRAVE_RAG_WEB_SEARCH_CHUNK_NUMBER,
+    **kwargs, # Additional search parameters like session with access_token
 )
 ```
 

env.d/development/common.e2e.dist

@@ -8,3 +8,5 @@ LLM_CONFIGURATION_FILE_PATH = /app/conversations/configuration/llm/default.e2e.j
 # Features
 FEATURE_FLAG_WEB_SEARCH=ENABLED
 FEATURE_FLAG_DOCUMENT_UPLOAD=ENABLED
+
+AUTO_TITLE_AFTER_USER_MESSAGES=3

src/backend/chat/agent_rag/document_converter/parser.py

@@ -0,0 +1,66 @@
+"""Document parsers for RAG backends."""
+
+import logging
+from io import BytesIO
+from urllib.parse import urljoin
+
+from django.conf import settings
+
+import requests
+
+from chat.agent_rag.document_converter.markitdown import DocumentConverter
+
+logger = logging.getLogger(__name__)
+
+
+class BaseParser:
+    """Base class for document parsers."""
+
+    def parse_document(self, name: str, content_type: str, content: BytesIO) -> str:
+        """
+        Parse the document and prepare it for the search operation.
+        This method should handle the logic to convert the document
+        into a format suitable for storage.
+
+        Args:
+            name (str): The name of the document.
+            content_type (str): The MIME type of the document (e.g., "application/pdf").
+            content (BytesIO): The content of the document as a BytesIO stream.
+
+        Returns:
+            str: The document content in Markdown format.
+        """
+        raise NotImplementedError("Must be implemented in subclass.")
+
+
+class AlbertParser(BaseParser):
+    """Document parser using Albert API for PDFs and DocumentConverter for other formats."""
+
+    endpoint = urljoin(settings.ALBERT_API_URL, "/v1/parse-beta")
+
+    def parse_pdf_document(self, name: str, content_type: str, content: bytes) -> str:
+        """Parse PDF document using Albert API."""
+        response = requests.post(
+            self.endpoint,
+            headers={
+                "Authorization": f"Bearer {settings.ALBERT_API_KEY}",
+            },
+            files={
+                "file": (name, content, content_type),
+                "output_format": (None, "markdown"),
+            },
+            timeout=settings.ALBERT_API_PARSE_TIMEOUT,
+        )
+        response.raise_for_status()
+
+        return "\n\n".join(
+            document_page["content"] for document_page in response.json().get("data", [])
+        )
+
+    def parse_document(self, name: str, content_type: str, content: bytes) -> str:
+        """Parse document based on content type."""
+        if content_type == "application/pdf":
+            return self.parse_pdf_document(name=name, content_type=content_type, content=content)
+        return DocumentConverter().convert_raw(
+            name=name, content_type=content_type, content=content
+        )

src/backend/chat/agent_rag/document_rag_backends/albert_rag_backend.py

@@ -13,174 +13,11 @@ import requests
 
 from chat.agent_rag.albert_api_constants import Searches
 from chat.agent_rag.constants import RAGWebResult, RAGWebResults, RAGWebUsage
-from chat.agent_rag.document_converter.markitdown import DocumentConverter
+from chat.agent_rag.document_converter.parser import AlbertParser
 from chat.agent_rag.document_rag_backends.base_rag_backend import BaseRagBackend
 
 logger = logging.getLogger(__name__)
 
-# Albert API token limit for document vectorization
-# We use a conservative chunk size to stay well under the limit
-ALBERT_MAX_TOKENS = 8192
-ALBERT_CHUNK_SIZE_TOKENS = 5000  # More conservative chunk size with larger safety margin
-# Approximate tokens: ~3 characters per token (more conservative estimate for Markdown/Excel)
-# Markdown and Excel content often have more tokens per character due to formatting
-ALBERT_CHUNK_SIZE_CHARS = ALBERT_CHUNK_SIZE_TOKENS * 3
-
-
-def _estimate_tokens(content: str) -> int:
-    """
-    Estimate the number of tokens in a text string.
-    
-    Uses a conservative approximation: ~3 characters per token.
-    This is more conservative than 4 chars/token to account for:
-    - Markdown formatting (headers, lists, tables)
-    - Excel content with special characters
-    - Whitespace and punctuation
-    
-    Args:
-        content (str): The text content to estimate.
-        
-    Returns:
-        int: Estimated number of tokens.
-    """
-    return len(content) // 3
-
-
-def _chunk_content(content: str, max_chars: int = ALBERT_CHUNK_SIZE_CHARS) -> List[str]:
-    """
-    Split content into chunks that fit within Albert's token limit.
-    
-    Attempts to split at paragraph boundaries (double newlines) when possible,
-    otherwise splits at line boundaries, and finally at character boundaries.
-    Validates that each chunk is under the token limit after splitting.
-    
-    Args:
-        content (str): The content to chunk.
-        max_chars (int): Maximum characters per chunk (default: ALBERT_CHUNK_SIZE_CHARS).
-        
-    Returns:
-        list[str]: List of content chunks, each under the token limit.
-    """
-    # First check if content fits in one chunk
-    estimated_tokens = _estimate_tokens(content)
-    if estimated_tokens <= ALBERT_CHUNK_SIZE_TOKENS:
-        return [content]
-    
-    chunks = []
-    remaining = content
-    
-    while len(remaining) > 0:
-        # Check if remaining content fits in one chunk
-        remaining_tokens = _estimate_tokens(remaining)
-        if remaining_tokens <= ALBERT_CHUNK_SIZE_TOKENS:
-            if remaining.strip():
-                chunks.append(remaining.strip())
-            break
-        
-        # Need to split - find the best split point
-        # Start with max_chars but may need to reduce if token estimate is too high
-        search_limit = max_chars
-        
-        # Try to find a split point that keeps us under token limit
-        # Reduce search limit if needed to ensure token limit is respected
-        while search_limit > 100:  # Minimum chunk size
-            # Try to split at paragraph boundary (double newline)
-            split_pos = remaining.rfind("\n\n", 0, search_limit)
-            if split_pos == -1:
-                # Try to split at single newline
-                split_pos = remaining.rfind("\n", 0, search_limit)
-            if split_pos == -1:
-                # Force split at character boundary
-                split_pos = search_limit
-            
-            # Validate that this chunk is under token limit
-            chunk_candidate = remaining[:split_pos].strip()
-            if chunk_candidate:
-                chunk_tokens = _estimate_tokens(chunk_candidate)
-                if chunk_tokens <= ALBERT_CHUNK_SIZE_TOKENS:
-                    chunks.append(chunk_candidate)
-                    remaining = remaining[split_pos:].lstrip()
-                    break
-            
-            # Chunk too large, reduce search limit and try again
-            search_limit = int(search_limit * 0.8)  # Reduce by 20%
-        else:
-            # Fallback: force split at a safe size
-            # This should rarely happen, but ensures we don't get stuck
-            safe_size = min(max_chars, len(remaining))
-            chunk = remaining[:safe_size].strip()
-            if chunk:
-                chunks.append(chunk)
-            remaining = remaining[safe_size:].lstrip()
-    
-    # Validate all chunks are under limit and split further if needed
-    validated_chunks = []
-    for chunk_item in chunks:
-        chunk_tokens = _estimate_tokens(chunk_item)
-        if chunk_tokens > ALBERT_MAX_TOKENS:
-            logger.warning(
-                "Chunk still exceeds token limit (%d tokens, max: %d), forcing split further",
-                chunk_tokens,
-                ALBERT_MAX_TOKENS,
-            )
-            # Force split this chunk further using a more conservative size
-            # Use a size that ensures we stay well under the token limit
-            # Target: ~5000 tokens max per chunk (conservative)
-            max_safe_chars = ALBERT_CHUNK_SIZE_TOKENS * 3  # 6000 * 3 = 18000 chars for ~5000 tokens
-            remaining_chunk = chunk_item
-            while len(remaining_chunk) > 0:
-                remaining_tokens = _estimate_tokens(remaining_chunk)
-                if remaining_tokens <= ALBERT_CHUNK_SIZE_TOKENS:
-                    if remaining_chunk.strip():
-                        validated_chunks.append(remaining_chunk.strip())
-                    break
-                
-                # Find a safe split point
-                split_pos = min(max_safe_chars, len(remaining_chunk))
-                # Try to split at a line boundary if possible
-                line_split = remaining_chunk.rfind("\n", 0, split_pos)
-                if line_split > max_safe_chars * 0.5:  # Only use if it's not too small
-                    split_pos = line_split
-                
-                sub_chunk = remaining_chunk[:split_pos].strip()
-                if sub_chunk:
-                    sub_tokens = _estimate_tokens(sub_chunk)
-                    # Double-check this sub-chunk is safe
-                    if sub_tokens > ALBERT_MAX_TOKENS:
-                        # Still too large, use even smaller size
-                        logger.warning(
-                            "Sub-chunk still too large (%d tokens), using smaller split",
-                            sub_tokens,
-                        )
-                        split_pos = ALBERT_CHUNK_SIZE_TOKENS * 2  # 12000 chars for ~3000 tokens
-                        sub_chunk = remaining_chunk[:split_pos].strip()
-                    validated_chunks.append(sub_chunk)
-                remaining_chunk = remaining_chunk[split_pos:].lstrip()
-        else:
-            validated_chunks.append(chunk_item)
-    
-    # Final validation - ensure NO chunk exceeds the limit
-    final_chunks = []
-    for chunk in validated_chunks:
-        chunk_tokens = _estimate_tokens(chunk)
-        if chunk_tokens > ALBERT_MAX_TOKENS:
-            logger.error(
-                "CRITICAL: Chunk still exceeds limit after all splitting attempts: %d tokens",
-                chunk_tokens,
-            )
-            # Emergency split: use very conservative size
-            emergency_size = ALBERT_CHUNK_SIZE_TOKENS * 2  # 12000 chars
-            remaining = chunk
-            while len(remaining) > 0:
-                emergency_chunk = remaining[:emergency_size].strip()
-                if emergency_chunk:
-                    final_chunks.append(emergency_chunk)
-                remaining = remaining[emergency_size:].lstrip()
-        else:
-            final_chunks.append(chunk)
-    
-    return final_chunks
-
 
 class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-attributes
     """
@@ -189,9 +26,6 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
 
     It provides methods to:
     - Create a collection for the search operation.
-    - Parse documents and convert them to Markdown format:
-       + Handle PDF parsing using the Albert API.
-       + Use the DocumentConverter (markitdown) for other formats.
     - Store parsed documents in the Albert collection.
     - Perform a search operation using the Albert API.
     """
@@ -209,10 +43,9 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
         }
         self._collections_endpoint = urljoin(self._base_url, "/v1/collections")
         self._documents_endpoint = urljoin(self._base_url, "/v1/documents")
-        self._pdf_parser_endpoint = urljoin(self._base_url, "/v1/parse-beta")
         self._search_endpoint = urljoin(self._base_url, "/v1/search")
-
         self._default_collection_description = "Temporary collection for RAG document search"
+        self.parser = AlbertParser()
 
     def create_collection(self, name: str, description: Optional[str] = None) -> str:
         """
@@ -254,7 +87,7 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
         self.collection_id = str(response.json()["id"])
         return self.collection_id
 
-    def delete_collection(self) -> None:
+    def delete_collection(self, **kwargs) -> None:
         """
         Delete the current collection
         """
@@ -265,7 +98,7 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
         )
         response.raise_for_status()
 
-    async def adelete_collection(self) -> None:
+    async def adelete_collection(self, **kwargs) -> None:
         """
         Asynchronously delete the current collection
         """
@@ -277,101 +110,15 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
             )
             response.raise_for_status()
 
-    def parse_pdf_document(self, name: str, content_type: str, content: BytesIO) -> str:
-        """
-        Parse the PDF document content and return the text content.
-        This method should handle the logic to convert the PDF into
-        a format suitable for the Albert API.
-        """
-        response = requests.post(
-            self._pdf_parser_endpoint,
-            headers=self._headers,
-            files={
-                "file": (
-                    name,
-                    content,
-                    content_type,
-                ),  # Use the name as the filename in the request
-                "output_format": (None, "markdown"),  # Specify the output format as Markdown,
-            },
-            timeout=settings.ALBERT_API_PARSE_TIMEOUT,
-        )
-        response.raise_for_status()
-
-        return "\n\n".join(
-            document_page["content"] for document_page in response.json().get("data", [])
-        )
-
-    def parse_document(self, name: str, content_type: str, content: BytesIO):
-        """
-        Parse the document and prepare it for the search operation.
-        This method should handle the logic to convert the document
-        into a format suitable for the Albert API.
-
-        Args:
-            name (str): The name of the document.
-            content_type (str): The MIME type of the document (e.g., "application/pdf").
-            content (BytesIO): The content of the document as a BytesIO stream.
-
-        Returns:
-            str: The document content in Markdown format.
-        """
-        # Implement the parsing logic here
-        if content_type == "application/pdf":
-            # Handle PDF parsing
-            markdown_content = self.parse_pdf_document(
-                name=name, content_type=content_type, content=content
-            )
-        else:
-            markdown_content = DocumentConverter().convert_raw(
-                name=name, content_type=content_type, content=content
-            )
-
-        return markdown_content
-
-    def store_document(self, name: str, content: str) -> None:
+    def store_document(self, name: str, content: str, **kwargs) -> None:
         """
         Store the document content in the Albert collection.
         This method should handle the logic to send the document content to the Albert API.
-        
-        If the document is too large (exceeds Albert's token limit), it will be automatically
-        split into multiple chunks and stored as separate documents.
 
         Args:
             name (str): The name of the document.
             content (str): The content of the document in Markdown format.
-        """
-        # Check if content needs to be chunked
-        estimated_tokens = _estimate_tokens(content)
-        
-        if estimated_tokens > ALBERT_MAX_TOKENS:
-            logger.info(
-                "Document '%s' is too large (%d estimated tokens, limit: %d). "
-                "Splitting into chunks.",
-                name,
-                estimated_tokens,
-                ALBERT_MAX_TOKENS,
-            )
-            chunks = _chunk_content(content)
-            logger.info("Split document '%s' into %d chunks", name, len(chunks))
-            
-            # Store each chunk as a separate document
-            for i, chunk in enumerate(chunks, start=1):
-                chunk_name = f"{name}_part_{i}" if len(chunks) > 1 else name
-                self._store_single_document(chunk_name, chunk)
-        else:
-            # Document fits within limit, store as-is
-            self._store_single_document(name, content)
-    
-    def _store_single_document(self, name: str, content: str) -> None:
-        """
-        Store a single document chunk in the Albert collection.
-        
-        Internal method that performs the actual API call to store one document.
-        
-        Args:
-            name (str): The name of the document.
-            content (str): The content of the document in Markdown format.
+            **kwargs: Additional arguments.
         """
         response = requests.post(
             urljoin(self._base_url, self._documents_endpoint),
@@ -383,71 +130,18 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
             },
             timeout=settings.ALBERT_API_TIMEOUT,
         )
-        logger.debug("Stored document '%s': %s", name, response.json())
+        logger.debug(response.json())
         response.raise_for_status()
 
-    async def astore_document(self, name: str, content: str) -> None:
+    async def astore_document(self, name: str, content: str, **kwargs) -> None:
         """
         Store the document content in the Albert collection.
         This method should handle the logic to send the document content to the Albert API.
-        
-        If the document is too large (exceeds Albert's token limit), it will be automatically
-        split into multiple chunks and stored as separate documents.
 
         Args:
             name (str): The name of the document.
             content (str): The content of the document in Markdown format.
-        """
-        # Check if content needs to be chunked
-        estimated_tokens = _estimate_tokens(content)
-        
-        if estimated_tokens > ALBERT_MAX_TOKENS:
-            logger.info(
-                "Document '%s' is too large (%d estimated tokens, limit: %d). "
-                "Splitting into chunks.",
-                name,
-                estimated_tokens,
-                ALBERT_MAX_TOKENS,
-            )
-            chunks = _chunk_content(content)
-            logger.info("Split document '%s' into %d chunks", name, len(chunks))
-            
-            # Validate chunks before storing
-            for i, chunk in enumerate(chunks, start=1):
-                chunk_tokens = _estimate_tokens(chunk)
-                logger.debug(
-                    "Chunk %d/%d: %d chars, ~%d tokens",
-                    i,
-                    len(chunks),
-                    len(chunk),
-                    chunk_tokens,
-                )
-                if chunk_tokens > ALBERT_MAX_TOKENS:
-                    logger.error(
-                        "Chunk %d/%d still exceeds token limit: %d tokens (max: %d)",
-                        i,
-                        len(chunks),
-                        chunk_tokens,
-                        ALBERT_MAX_TOKENS,
-                    )
-            
-            # Store each chunk as a separate document
-            for i, chunk in enumerate(chunks, start=1):
-                chunk_name = f"{name}_part_{i}" if len(chunks) > 1 else name
-                await self._astore_single_document(chunk_name, chunk)
-        else:
-            # Document fits within limit, store as-is
-            await self._astore_single_document(name, content)
-    
-    async def _astore_single_document(self, name: str, content: str) -> None:
-        """
-        Store a single document chunk in the Albert collection.
-        
-        Internal method that performs the actual API call to store one document.
-        
-        Args:
-            name (str): The name of the document.
-            content (str): The content of the document in Markdown format.
+            **kwargs: Additional arguments.
         """
         async with httpx.AsyncClient(timeout=settings.ALBERT_API_TIMEOUT) as client:
             response = await client.post(
@@ -462,16 +156,17 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
                 },
                 timeout=settings.ALBERT_API_TIMEOUT,
             )
-            logger.debug("Stored document '%s': %s", name, response.json())
+            logger.debug(response.json())
             response.raise_for_status()
 
-    def search(self, query, results_count: int = 4) -> RAGWebResults:
+    def search(self, query: str, results_count: int = 4, **kwargs) -> RAGWebResults:
         """
         Perform a search using the Albert API based on the provided query.
 
         Args:
             query (str): The search query.
             results_count (int): The number of results to return.
+            **kwargs: Additional arguments.
 
         Returns:
             RAGWebResults: The search results.
@@ -508,13 +203,14 @@ class AlbertRagBackend(BaseRagBackend):  # pylint: disable=too-many-instance-att
             ),
         )
 
-    async def asearch(self, query, results_count: int = 4) -> RAGWebResults:
+    async def asearch(self, query, results_count: int = 4, **kwargs) -> RAGWebResults:
         """
         Perform an asynchronous search using the Albert API based on the provided query.
 
         Args:
             query (str): The search query.
             results_count (int): The number of results to return.
+            **kwargs: Additional arguments.
 
         Returns:
             RAGWebResults: The search results.

src/backend/chat/agent_rag/document_rag_backends/base_rag_backend.py

@@ -1,6 +1,7 @@
 """Implementation of the Albert API for RAG document search."""
 
 import logging
+from abc import ABC, abstractmethod
 from contextlib import asynccontextmanager, contextmanager
 from io import BytesIO
 from typing import List, Optional
@@ -8,11 +9,12 @@ from typing import List, Optional
 from asgiref.sync import sync_to_async
 
 from chat.agent_rag.constants import RAGWebResults
+from chat.agent_rag.document_converter.parser import BaseParser
 
 logger = logging.getLogger(__name__)
 
 
-class BaseRagBackend:
+class BaseRagBackend(ABC):
     """Base class for RAG backends."""
 
     def __init__(
@@ -38,6 +40,7 @@ class BaseRagBackend:
         self.collection_id = collection_id
         self.read_only_collection_id = read_only_collection_id or []
         self._default_collection_description = "Temporary collection for RAG document search"
+        self.parser: BaseParser = BaseParser()
 
     def get_all_collection_ids(self) -> List[str]:
         """
@@ -53,13 +56,14 @@ class BaseRagBackend:
 
         collection_ids = []
         if self.collection_id:
-            collection_ids.append(int(self.collection_id))
+            collection_ids.append(self.collection_id)
         if self.read_only_collection_id:
             collection_ids.extend(
                 [int(collection_id) for collection_id in self.read_only_collection_id]
             )
         return collection_ids
 
+    @abstractmethod
     def create_collection(self, name: str, description: Optional[str] = None) -> str:
         """
         Create a temporary collection for the search operation.
@@ -88,9 +92,10 @@ class BaseRagBackend:
         Returns:
             str: The document content in Markdown format.
         """
-        raise NotImplementedError("Must be implemented in subclass.")
+        return self.parser.parse_document(name, content_type, content)
 
-    def store_document(self, name: str, content: str) -> None:
+    @abstractmethod
+    def store_document(self, name: str, content: str, **kwargs) -> None:
         """
         Store the document content in the collection.
         This method should handle the logic to send the document content to the API.
@@ -98,10 +103,11 @@ class BaseRagBackend:
         Args:
             name (str): The name of the document.
             content (str): The content of the document in Markdown format.
+            **kwargs: Additional arguments. ex: "user_sub" for access control.
         """
         raise NotImplementedError("Must be implemented in subclass.")
 
-    async def astore_document(self, name: str, content: str) -> None:
+    async def astore_document(self, name: str, content: str, **kwargs) -> None:
         """
         Store the document content in the collection.
         This method should handle the logic to send the document content to the API.
@@ -109,10 +115,13 @@ class BaseRagBackend:
         Args:
             name (str): The name of the document.
             content (str): The content of the document in Markdown format.
+            **kwargs: Additional arguments. ex: "user_sub" for access control.
         """
-        return await sync_to_async(self.store_document)(name=name, content=content)
+        return await sync_to_async(self.store_document)(name=name, content=content, **kwargs)
 
-    def parse_and_store_document(self, name: str, content_type: str, content: BytesIO) -> str:
+    def parse_and_store_document(
+        self, name: str, content_type: str, content: BytesIO, **kwargs
+    ) -> str:
         """
         Parse the document and store it in the Albert collection.
 
@@ -120,39 +129,52 @@ class BaseRagBackend:
             name (str): The name of the document.
             content_type (str): The MIME type of the document (e.g., "application/pdf").
             content (BytesIO): The content of the document as a BytesIO stream.
+            **kwargs: Additional arguments. ex: "user_sub" for access control.
         """
         if not self.collection_id:
             raise RuntimeError("The RAG backend requires collection_id")
 
         document_content = self.parse_document(name, content_type, content)
-        self.store_document(name, document_content)
+        self.store_document(name, document_content, **kwargs)
         return document_content
 
-    def delete_collection(self) -> None:
+    @abstractmethod
+    def delete_collection(self, **kwargs) -> None:
         """
         Delete the collection.
         This method should handle the logic to delete the collection from the backend.
         """
         raise NotImplementedError("Must be implemented in subclass.")
 
-    async def adelete_collection(self) -> None:
+    async def adelete_collection(self, **kwargs) -> None:
         """
         Delete the collection.
         This method should handle the logic to delete the collection from the backend.
         """
-        return await sync_to_async(self.delete_collection)()
+        return await sync_to_async(self.delete_collection)(**kwargs)
 
-    def search(self, query, results_count: int = 4) -> RAGWebResults:
+    @abstractmethod
+    def search(self, query: str, results_count: int = 4, **kwargs) -> RAGWebResults:
         """
         Search the collection for the given query.
+
+        Args:
+            query: The search query string.
+            results_count: Number of results to return.
+            **kwargs: Additional arguments. ex: 'session' for OIDC authentication.
         """
         raise NotImplementedError("Must be implemented in subclass.")
 
-    async def asearch(self, query, results_count: int = 4) -> RAGWebResults:
+    async def asearch(self, query: str, results_count: int = 4, **kwargs) -> RAGWebResults:
         """
-        Search the collection for the given query.
+        Search the collection for the given query asynchronously.
+
+        Args:
+            query: The search query string.
+            results_count: Number of results to return.
+            **kwargs: Additional arguments. ex: 'session' for OIDC authentication.
         """
-        return await sync_to_async(self.search)(query=query, results_count=results_count)
+        return await sync_to_async(self.search)(query=query, results_count=results_count, **kwargs)
 
     @classmethod
     @contextmanager
@@ -168,7 +190,9 @@ class BaseRagBackend:
 
     @classmethod
     @asynccontextmanager
-    async def temporary_collection_async(cls, name: str, description: Optional[str] = None):
+    async def temporary_collection_async(
+        cls, name: str, description: Optional[str] = None, **kwargs
+    ):
         """Context manager for RAG backend with temporary collections."""
         backend = cls()
 
@@ -176,4 +200,4 @@ class BaseRagBackend:
         try:
             yield backend
         finally:
-            await backend.adelete_collection()
+            await backend.adelete_collection(**kwargs)

src/backend/chat/agent_rag/document_rag_backends/find_rag_backend.py

@@ -0,0 +1,163 @@
+"""Implementation of the Find API for RAG document search."""
+
+import logging
+import uuid
+from typing import List, Optional
+from urllib.parse import urljoin
+from uuid import uuid4
+
+from django.conf import settings
+from django.utils import timezone
+
+import requests
+
+from chat.agent_rag.constants import RAGWebResult, RAGWebResults, RAGWebUsage
+from chat.agent_rag.document_converter.parser import AlbertParser
+from chat.agent_rag.document_rag_backends.base_rag_backend import BaseRagBackend
+from utils.oidc import with_fresh_access_token
+
+logger = logging.getLogger(__name__)
+
+
+SUPPORTED_LANGUAGE_CODES = ["en", "fr", "de", "nl"]
+
+
+class FindRagBackend(BaseRagBackend):
+    """
+    This class is a placeholder for the Find API implementation.
+    It is designed to be used with the RAG (Retrieval-Augmented Generation) document search system.
+
+    It provides methods to:
+    - Store parsed documents in the Find index.
+    - Perform a search operation using the Find API.
+    """
+
+    def __init__(
+        self,
+        collection_id: Optional[str] = None,
+        read_only_collection_id: Optional[List[str]] = None,
+    ):
+        # Initialize any necessary parameters or configurations here
+        super().__init__(collection_id, read_only_collection_id)
+        self.api_key = settings.FIND_API_KEY
+        self.search_endpoint = "api/v1.0/documents/search/"
+        self.indexing_endpoint = "api/v1.0/documents/index/"
+        self.deleting_endpoint = "api/v1.0/documents/delete/"
+        self.parser = AlbertParser()  # Find Rag relies on Albert parser
+
+    def create_collection(self, name: str, description: Optional[str] = None) -> str:
+        """
+        init collection_id
+        """
+        self.collection_id = self.collection_id or str(uuid.uuid4())
+        return self.collection_id
+
+    @with_fresh_access_token
+    def delete_collection(self, **kwargs) -> None:
+        """
+        Delete the current collection
+        """
+        response = requests.post(
+            urljoin(settings.FIND_API_URL, self.deleting_endpoint),
+            headers={"Authorization": f"Bearer {kwargs['session'].get('oidc_access_token')}"},
+            json={
+                "tags": [f"collection-{self.collection_id}"],
+                # "service": "conversations"
+            },
+            timeout=settings.FIND_API_TIMEOUT,
+        )
+        response.raise_for_status()
+
+    def store_document(self, name: str, content: str, **kwargs) -> None:
+        """
+        index document in Find
+
+        Args:
+            name (str): The name of the document.
+            content (str): The content of the document in Markdown format.
+            user_sub (str): The user subject identifier for access control.
+        """
+        logger.debug("index document '%s' in Find", name)
+
+        user_sub = kwargs.get("user_sub")
+        if not user_sub:
+            raise ValueError("user_sub is required to store document in FindRagBackend")
+
+        response = requests.post(
+            urljoin(settings.FIND_API_URL, self.indexing_endpoint),
+            headers={"Authorization": f"Bearer {self.api_key}"},
+            json={
+                "id": str(uuid4()),
+                "title": str(name) or "",
+                "depth": 0,
+                "path": str(name) or "",
+                "numchild": 0,
+                "content": content or "",
+                "created_at": timezone.now().isoformat(),
+                "updated_at": timezone.now().isoformat(),
+                "tags": [f"collection-{self.collection_id}"],
+                "size": len(content.encode("utf-8")),
+                "users": [user_sub],
+                "groups": [],
+                "reach": "authenticated",
+                "is_active": True,
+            },
+            timeout=settings.FIND_API_TIMEOUT,
+        )
+        response.raise_for_status()
+
+    @with_fresh_access_token
+    def search(self, query: str, results_count: int = 4, **kwargs) -> RAGWebResults:
+        """
+        Perform a search using the Find API.
+        Uses the user's OIDC token from the request session.
+
+        Args:
+            query: The search query.
+            results_count: Number of results to return.
+            **kwargs: Additional arguments. Expected: 'session' containing OIDC tokens,
+
+        Returns:
+            RAGWebResults: The search results.
+        """
+        logger.debug("search documents in Find with query '%s'", query)
+        response = requests.post(
+            urljoin(settings.FIND_API_URL, self.search_endpoint),
+            headers={"Authorization": f"Bearer {kwargs['session'].get('oidc_access_token')}"},
+            json={
+                "q": query or "*",
+                "tags": [
+                    f"collection-{collection_id}" for collection_id in self.get_all_collection_ids()
+                ],
+                "k": results_count,
+            },
+            timeout=settings.FIND_API_TIMEOUT,
+        )
+        response.raise_for_status()
+
+        return RAGWebResults(
+            data=[
+                RAGWebResult(
+                    url=get_language_value(result["_source"], "title"),
+                    content=get_language_value(result["_source"], "content"),
+                    score=result["_score"],
+                )
+                for result in response.json()
+            ],
+            usage=RAGWebUsage(
+                prompt_tokens=0,
+                completion_tokens=0,
+            ),
+        )
+
+
+def get_language_value(source, language_field):
+    """
+    extract the value of the language field with the correct language_code extension.
+    "title" and "content" have extensions like "title.en" or "title.fr".
+    get_language_value will return the value regardless of the extension.
+    """
+    for language_code in SUPPORTED_LANGUAGE_CODES:
+        if f"{language_field}.{language_code}" in source:
+            return source[f"{language_field}.{language_code}"]
+    raise ValueError(f"No '{language_field}' field with any supported language code in object")

src/backend/chat/agents/base.py

@@ -10,7 +10,6 @@ import httpx
 from pydantic_ai import Agent
 from pydantic_ai.models import get_user_agent
 from pydantic_ai.profiles import ModelProfile
-from pydantic_ai.toolsets import FunctionToolset
 
 from chat.tools import get_pydantic_tools_by_name
 
@@ -174,20 +173,18 @@ class BaseAgent(Agent):
             # and pydantic_ai.models.infer_model()
             _model_instance = self.configuration.model_name
 
-        _system_prompt = self.configuration.system_prompt
-        _base_toolset = (
-            [
-                FunctionToolset(
-                    tools=[
-                        get_pydantic_tools_by_name(tool_name)
-                        for tool_name in self.configuration.tools
-                    ]
-                )
-            ]
-            if self.configuration.tools
-            else None
-        )
+        _system_prompt = self.get_system_prompt()
 
-        _tools = [get_pydantic_tools_by_name(tool_name) for tool_name in self.configuration.tools]
+        _tools = self.get_tools()
 
         super().__init__(model=_model_instance, instructions=_system_prompt, tools=_tools, **kwargs)
+
+    def get_system_prompt(self) -> str | None:
+        """Override this method to customize the system prompt."""
+        return self.configuration.system_prompt
+
+    def get_tools(self) -> list | None:
+        """Override this method to customize tools."""
+        if not self.configuration.tools:
+            return []
+        return [get_pydantic_tools_by_name(tool_name) for tool_name in self.configuration.tools]

src/backend/chat/agents/conversation.py

@@ -131,3 +131,25 @@ class ConversationAgent(BaseAgent):
                 if tool.name.startswith("web_search_"):
                     return tool.name
         return None
+
+
+@dataclasses.dataclass(init=False)
+class TitleGenerationAgent(BaseAgent):
+    """Agent that generates concise, descriptive titles for conversations."""
+
+    def __init__(self, **kwargs):
+        super().__init__(
+            model_hrid=settings.LLM_DEFAULT_MODEL_HRID,
+            output_type=str,
+            **kwargs,
+        )
+
+    def get_tools(self):
+        return []
+
+    def get_system_prompt(self):
+        return (
+            "You are a title generator. Your task is to create concise, descriptive titles "
+            "that accurately summarize conversation content and help the user quickly identify the "
+            "conversation.\n\n"
+        )

src/backend/chat/clients/pydantic_ai.py

@@ -52,10 +52,9 @@ from pydantic_ai.messages import (
 )
 
 from core.feature_flags.helpers import is_feature_enabled
-from core.file_upload.utils import generate_retrieve_policy
 
 from chat import models
-from chat.agents.conversation import ConversationAgent
+from chat.agents.conversation import ConversationAgent, TitleGenerationAgent
 from chat.agents.local_media_url_processors import (
     update_history_local_urls,
     update_local_urls,
@@ -72,12 +71,11 @@ from chat.clients.pydantic_ui_message_converter import (
     ui_message_to_user_content,
 )
 from chat.mcp_servers import get_mcp_servers
-from chat.tools.data_analysis import add_data_analysis_tool
 from chat.tools.document_generic_search_rag import add_document_rag_search_tool_from_setting
 from chat.tools.document_search_rag import add_document_rag_search_tool
 from chat.tools.document_summarize import document_summarize
 from chat.vercel_ai_sdk.core import events_v4, events_v5
-from chat.vercel_ai_sdk.encoder import EventEncoder
+from chat.vercel_ai_sdk.encoder import CURRENT_EVENT_ENCODER_VERSION, EventEncoder
 
 # Keep at the top of the file to avoid mocking issues
 document_store_backend = import_string(settings.RAG_DOCUMENT_SEARCH_BACKEND)
@@ -93,6 +91,7 @@ class ContextDeps:
 
     conversation: models.ChatConversation
     user: User
+    session: Optional[Dict] = None
     web_search_enabled: bool = False
 
 
@@ -107,7 +106,14 @@ def get_model_configuration(model_hrid: str):
 class AIAgentService:  # pylint: disable=too-many-instance-attributes
     """Service class for AI-related operations (Pydantic-AI edition)."""
 
-    def __init__(self, conversation: models.ChatConversation, user, model_hrid=None, language=None):
+    def __init__(  # pylint: disable=too-many-arguments,too-many-positional-arguments
+        self,
+        conversation: models.ChatConversation,
+        user,
+        session=None,
+        model_hrid=None,
+        language=None,
+    ):
         """
         Initialize the AI agent service.
 
@@ -123,7 +129,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
 
         self._langfuse_available = settings.LANGFUSE_ENABLED
         self._store_analytics = self._langfuse_available and user.allow_conversation_analytics
-        self.event_encoder = EventEncoder("v4")  # Always use v4 for now
+        self.event_encoder = EventEncoder(CURRENT_EVENT_ENCODER_VERSION)  # We use v4 for now
 
         self._support_streaming = True
         if (streaming := get_model_configuration(self.model_hrid).supports_streaming) is not None:
@@ -137,6 +143,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
         self._context_deps = ContextDeps(
             conversation=conversation,
             user=user,
+            session=session,
             web_search_enabled=self._is_web_search_enabled,
         )
 
@@ -152,7 +159,6 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
             deps_type=ContextDeps,
         )
         add_document_rag_search_tool_from_setting(self.conversation_agent, self.user)
-        add_data_analysis_tool(self.conversation_agent)
 
     @property
     def _stop_cache_key(self):
@@ -280,6 +286,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
                         name=document.identifier,
                         content_type=document.media_type,
                         content=document_data,
+                        user_sub=self.user.sub,
                     )
                 else:
                     # Remote URL
@@ -289,26 +296,10 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
                     name=document.identifier,
                     content_type=document.media_type,
                     content=document.data,
+                    user_sub=self.user.sub,
                 )
 
-            # Don't convert tabular files (CSV, Excel) to Markdown - keep originals for data_analysis tool
-            # Tabular files are already text-based or can be used directly
-            is_tabular_file = (
-                document.media_type in [
-                    "text/csv",
-                    "application/csv",
-                    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
-                    "application/vnd.ms-excel",
-                    "application/excel",
-                ]
-                or any(
-                    document.identifier.lower().endswith(ext)
-                    for ext in [".csv", ".xlsx", ".xls", ".xlsm", ".xlsb"]
-                )
-            )
-            
-            # Only convert non-text files that are not tabular files
-            if not document.media_type.startswith("text/") and not is_tabular_file:
+            if not document.media_type.startswith("text/"):
                 md_attachment = await models.ChatConversationAttachment.objects.acreate(
                     conversation=self.conversation,
                     uploaded_by=self.user,
@@ -490,28 +481,19 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
         _tool_is_streaming = False
         _model_response_message_id = None
 
-        # Check for existing non-PDF documents in the conversation:
-        # - if no document at all: do nothing
-        # - if only PDFs: prepare document URLs for the agent
-        # - if other document types: add the RAG search tool
-        #   to allow searching in all kinds of documents
-        has_not_pdf_docs = await (
+        # Check for existing documents (any non-image attachment for this conversation)
+        has_documents = await (
             models.ChatConversationAttachment.objects.filter(
                 Q(conversion_from__isnull=True) | Q(conversion_from=""),
                 conversation=self.conversation,
             )
-            .exclude(
-                Q(content_type__startswith="image/") | Q(content_type="application/pdf"),
-            )
+            .exclude(content_type__startswith="image/")
             .aexists()
         )
 
+        should_enable_rag = conversation_has_documents or has_documents
 
-        document_urls = []
-        if not conversation_has_documents and not has_not_pdf_docs:
-            # No documents to process
-            pass
-        elif has_not_pdf_docs:
+        if should_enable_rag:
             add_document_rag_search_tool(self.conversation_agent)
 
             @self.conversation_agent.instructions
@@ -542,37 +524,6 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
                 """Wrap the document_summarize tool to provide context and add the tool."""
                 return await document_summarize(ctx, *args, **kwargs)
 
-        if not conversation_has_documents and not has_not_pdf_docs:
-            # No documents to process
-            pass
-        elif has_not_pdf_docs:
-            # Already handled above with RAG tool
-            pass
-        else:
-            conversation_documents = [
-                cd
-                async for cd in models.ChatConversationAttachment.objects.filter(
-                    Q(conversion_from__isnull=True) | Q(conversion_from=""),
-                    conversation=self.conversation,
-                )
-                .exclude(
-                    content_type__startswith="image/",
-                )
-                .values_list("key", "content_type")
-            ]
-
-            for doc_key, doc_content_type in conversation_documents:
-                if doc_content_type == "application/pdf":
-                    _presigned_url = generate_retrieve_policy(doc_key)
-                    document_urls.append(
-                        DocumentUrl(
-                            url=_presigned_url,
-                            identifier=doc_key.split("/")[-1],
-                            media_type="application/pdf",
-                        )
-                    )
-                    image_key_mapping[_presigned_url] = f"/media-key/{doc_key}"
-
         async with AsyncExitStack() as stack:
             # MCP servers (if any) can be initialized here
             mcp_servers = [await stack.enter_async_context(mcp) for mcp in get_mcp_servers()]
@@ -586,7 +537,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
                     history.append(ModelResponse(parts=[TextPart(content="ok")], kind="response"))
 
             async with self.conversation_agent.iter(
-                [user_prompt] + input_images + document_urls,
+                [user_prompt] + input_images,
                 message_history=history,  # history will pass through agent's history_processors
                 deps=self._context_deps,
                 toolsets=mcp_servers,
@@ -747,8 +698,8 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
 
         await self._agent_stop_streaming(force_cache_check=True)
 
-        # Persist conversation
-        await sync_to_async(self._update_conversation)(
+        # Prepare conversation update (save deferred until after potential title generation)
+        await sync_to_async(self._prepare_update_conversation)(
             final_output=run.result.new_messages(),
             usage=usage,
             final_output_from_tool=_final_output_from_tool,
@@ -757,6 +708,35 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
             image_key_mapping=image_key_mapping or None,
         )
 
+        generated_title = None
+
+        # Auto-generate title after N user messages if not manually set
+        user_messages_count = sum(1 for msg in self.conversation.messages if msg.role == "user")
+
+        should_generate_title = (
+            user_messages_count == settings.AUTO_TITLE_AFTER_USER_MESSAGES
+            and not self.conversation.title_set_by_user_at
+        )
+
+        if should_generate_title:
+            if generated_title := await self._generate_title():
+                self.conversation.title = generated_title
+
+        # Persist conversation (including any generated title)
+        await sync_to_async(self.conversation.save)()
+
+        # Notify frontend about the title update
+        if generated_title:
+            yield events_v4.DataPart(
+                data=[
+                    {
+                        "type": "conversation_metadata",
+                        "conversationId": str(self.conversation.pk),
+                        "title": generated_title,
+                    }
+                ]
+            )
+
         if self._langfuse_available:
             langfuse.update_current_trace(
                 output=run.result.output if self._store_analytics else "REDACTED"
@@ -770,7 +750,7 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
             ),
         )
 
-    def _update_conversation(  # noqa: PLR0913
+    def _prepare_update_conversation(  # noqa: PLR0913
         self,
         *,
         final_output: List[ModelRequest | ModelMessage],
@@ -837,4 +817,39 @@ class AIAgentService:  # pylint: disable=too-many-instance-attributes
             ModelMessagesTypeAdapter.dump_json(final_output).decode("utf-8")
         )
 
-        self.conversation.save()
+    async def _generate_title(self) -> str | None:
+        """Generate a title for the conversation using LLM based on first messages."""
+
+        # Build context from messages
+        # Note: We intentionally use only msg.content for title generation.
+        # Parts containing tool invocations or reasoning are excluded as they
+        # don't contribute to a meaningful context here
+        context = "\n".join(
+            f"{msg.role}: {(msg.content or '')[:300]}"  # Limit content length per message
+            for msg in self.conversation.messages
+            if msg.content
+        )
+
+        language = self.language or settings.LANGUAGE_CODE
+        prompt = (
+            "Generate a concise title (3-5 words, max 100 characters) for this conversation.\n\n"
+            "Requirements:\n"
+            "- Capture the main topic or user intent\n"
+            "- The title must be a simple string, no markdown\n"
+            "- Help the user quickly identify the conversation\n"
+            f"- Match the language of the user messages (default: {language})\n"
+            "- Avoid the word 'summary' unless explicitly requested\n\n"
+            "Output: Title text only, no quotes, labels, or explanation.\n\n"
+            f"Conversation:\n{context}"
+        )
+        try:
+            agent = TitleGenerationAgent()
+            result = await agent.run(prompt)
+            title = (result.output or "").strip()[:100]  # Enforce max length (conversation.title)
+            logger.info("Generated title for conversation %s: %s", self.conversation.pk, title)
+            return title if title else None
+        except Exception as exc:  # pylint: disable=broad-except #noqa: BLE001
+            logger.warning(
+                "Failed to generate title for conversation %s: %s", self.conversation.pk, exc
+            )
+            return None

src/backend/chat/keepalive.py

@@ -0,0 +1,171 @@
+"""Helpers to prevent proxy timeouts during long-running stream operations.
+
+This module provides utilities to wrap synchronous and asynchronous iterators
+with keepalive messages. When a stream pauses for longer than the specified
+interval, keepalive messages are injected to prevent proxy/gateway
+timeouts while waiting for the stream data.
+"""
+
+import asyncio
+import logging
+import queue
+import threading
+import time
+from typing import AsyncIterator, Iterator
+
+from django.conf import settings
+
+from .vercel_ai_sdk.core.events_v4 import DataPart as V4DataPart
+from .vercel_ai_sdk.core.events_v5 import DataPart as V5DataPart
+from .vercel_ai_sdk.encoder import (
+    CURRENT_EVENT_ENCODER_VERSION,
+    EventEncoder,
+    EventEncoderVersion,
+)
+
+logger = logging.getLogger(__name__)
+
+
+def get_keepalive_message() -> str:
+    """Generate a keepalive message based on encoder/SDK version."""
+    if CURRENT_EVENT_ENCODER_VERSION == EventEncoderVersion.V4:
+        event = V4DataPart(data=[{"status": "WAITING"}])
+    else:
+        event = V5DataPart(data={"status": "WAITING"})
+    encoder = EventEncoder(CURRENT_EVENT_ENCODER_VERSION)
+    return encoder.encode(event)
+
+
+async def stream_with_keepalive_async(
+    stream: AsyncIterator[str],
+) -> AsyncIterator[str]:
+    """Wrap an async iterator to emit keepalive during long pauses.
+
+    Args:
+        stream: The async iterator to wrap
+    Yields:
+        Items from the original stream, plus keepalive messages during pauses
+    Raises:
+        Any exception raised by the original stream
+    """
+    q: asyncio.Queue = asyncio.Queue()
+    finished = asyncio.Event()
+    keepalive_message = get_keepalive_message()
+
+    async def producer():
+        """Background task that consumes the original stream into a queue."""
+
+        try:
+            async for stream_item in stream:
+                await q.put(stream_item)
+        except Exception as exc:  # pylint: disable=broad-except #noqa: BLE001
+            # Pass exceptions through the queue so the consumer can re-raise them.
+            # This ensures errors aren't silently swallowed.
+            await q.put(exc)
+        finally:
+            finished.set()
+            await q.put(None)  # Sentinel to signal completion
+
+    producer_task = asyncio.create_task(producer())
+
+    try:
+        while True:
+            try:
+                item = await asyncio.wait_for(q.get(), timeout=settings.KEEPALIVE_INTERVAL)
+                if item is None:
+                    break
+                if isinstance(item, Exception):
+                    raise item
+                yield item
+            except asyncio.TimeoutError:
+                # No data received within interval
+                if finished.is_set():
+                    # Producer is done, queue is empty (else we would not have timed out)
+                    break
+
+                logger.debug("Send keepalive")
+                yield keepalive_message
+    finally:
+        # Cleanup
+        producer_task.cancel()
+        try:
+            await producer_task
+        except asyncio.CancelledError:
+            pass
+
+
+def get_current_time() -> float:
+    """Get current monotonic time, avoiding freezegun interferences.
+
+    Returns time.monotonic() which:
+    - Is NOT affected by freezegun's @freeze_time decorator (unlike time.time())
+    - Prevents issues where frozen time in main thread differs from real time in
+      spawned threads, causing incorrect keepalive interval computation
+    - Is the best clock for measuring time intervals
+
+    Wrapped in a function to ease mocking in tests.
+
+    Returns:
+        float: Monotonic time in seconds since an arbitrary reference point
+    """
+    return time.monotonic()
+
+
+def stream_with_keepalive_sync(stream: Iterator[str]) -> Iterator[str]:
+    """Wraps a synchronous stream with keepalive messages."""
+
+    q: queue.Queue = queue.Queue()
+    stream_done = threading.Event()
+    keepalive_message = get_keepalive_message()
+    # Mutable container so threads can read/write shared timestamp
+    last_yield_time = [get_current_time()]
+
+    def consume_stream():
+        """Read from source stream and forward chunks to queue."""
+        try:
+            for chunk in stream:
+                if stream_done.is_set():
+                    return  # early exit
+                q.put(chunk, timeout=1)  # Arbitrary timeout prevents blocking forever
+        # pylint: disable=broad-exception-caught
+        except Exception as e:
+            logger.exception("Error in stream consumption")
+            q.put(e)
+        finally:
+            stream_done.set()
+
+    def send_keepalives():
+        """Inject keepalive messages when idle too long.
+
+        Uses get_current_time() (time.monotonic) instead of time.time()
+        to avoid issues with freezegun in tests.
+        """
+        while not stream_done.is_set():
+            # Sleep before checking to give main loop time to process and update timestamp
+            time.sleep(0.5)  # let main loop process first, empiric value
+            if get_current_time() - last_yield_time[0] >= settings.KEEPALIVE_INTERVAL:
+                try:
+                    q.put(keepalive_message, timeout=0.1)
+                except queue.Full:
+                    pass
+
+    for target in (consume_stream, send_keepalives):
+        threading.Thread(target=target, daemon=True).start()
+
+    try:
+        # Continue while stream is active or queue has still items
+        while not stream_done.is_set() or not q.empty():
+            try:
+                item = q.get(timeout=1)  # short timeout, avoid blocking and stay responsive
+            except queue.Empty:
+                continue
+
+            # Re-raise from consume_stream
+            if isinstance(item, Exception):
+                raise item
+
+            yield item
+            last_yield_time[0] = get_current_time()
+    finally:
+        # Signal threads to stop
+        stream_done.set()

src/backend/chat/migrations/0005_chatconversation_title_set_by_user_at.py

@@ -0,0 +1,21 @@
+# Generated by Django 5.2.9 on 2025-12-30 09:44
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("chat", "0004_chatconversationattachment_and_more"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="chatconversation",
+            name="title_set_by_user_at",
+            field=models.DateTimeField(
+                blank=True,
+                help_text="Timestamp when the user manually set the title. If set, prevent automatic title generation.",
+                null=True,
+            ),
+        ),
+    ]

src/backend/chat/models.py

@@ -44,7 +44,12 @@ class ChatConversation(BaseModel):
         null=True,
         help_text="Title of the chat conversation",
     )
-
+    title_set_by_user_at = models.DateTimeField(
+        blank=True,
+        null=True,
+        help_text="Timestamp when the user manually set the title. If set, prevent automatic "
+        "title generation.",
+    )
     ui_messages = models.JSONField(
         default=list,
         blank=True,

src/backend/chat/serializers.py

@@ -4,6 +4,7 @@ from typing import Optional
 from urllib.parse import quote
 
 from django.conf import settings
+from django.utils import timezone
 
 from django_pydantic_field.rest_framework import SchemaField  # pylint: disable=no-name-in-module
 from drf_spectacular.utils import extend_schema_field
@@ -27,6 +28,12 @@ class ChatConversationSerializer(serializers.ModelSerializer):
         fields = ["id", "title", "created_at", "updated_at", "messages", "owner"]
         read_only_fields = ["id", "created_at", "updated_at", "messages"]
 
+    def update(self, instance, validated_data):
+        # If title is being changed, mark it as user-set
+        if "title" in validated_data and validated_data["title"] != instance.title:
+            instance.title_set_by_user_at = timezone.now()
+        return super().update(instance, validated_data)
+
 
 class ChatConversationInputSerializer(serializers.Serializer):
     """

src/backend/chat/tests/agents/test_title_generation_agent.py

@@ -0,0 +1,66 @@
+"""Test cases for the TitleGenerationAgent class."""
+
+# pylint: disable=protected-access
+
+import pytest
+from pydantic_ai.models.openai import OpenAIChatModel
+
+from chat.agents.conversation import TitleGenerationAgent
+
+
+@pytest.fixture(autouse=True)
+def base_settings(settings):
+    """Set up base settings for the tests."""
+    settings.AI_BASE_URL = "https://api.llm.com/v1/"
+    settings.AI_API_KEY = "test-key"
+    settings.AI_MODEL = "model-XYZ"
+    settings.AI_AGENT_INSTRUCTIONS = "You are a helpful assistant"
+    settings.AI_AGENT_TOOLS = []
+    settings.LLM_DEFAULT_MODEL_HRID = "default-model"
+
+
+def test_title_generation_agent_uses_default_model_hrid(settings):
+    """Test that TitleGenerationAgent uses LLM_DEFAULT_MODEL_HRID from settings."""
+    settings.AI_MODEL = "custom-llm-model"
+    settings.AI_BASE_URL = "https://custom.api.com/v1/"
+    settings.AI_API_KEY = "custom-key"
+    settings.LLM_DEFAULT_MODEL_HRID = "default-model"
+
+    agent = TitleGenerationAgent()
+
+    assert isinstance(agent._model, OpenAIChatModel)
+    assert settings.LLM_CONFIGURATIONS["default-model"].model_name == "custom-llm-model"
+    assert agent._model.model_name == "custom-llm-model"
+
+
+def test_title_generation_agent_model_configuration():
+    """Test that the agent model is properly configured."""
+    agent = TitleGenerationAgent()
+
+    assert isinstance(agent._model, OpenAIChatModel)
+    assert agent._model.model_name == "model-XYZ"
+    assert str(agent._model.client.base_url) == "https://api.llm.com/v1/"
+    assert agent._model.client.api_key == "test-key"
+
+
+def test_title_generation_agent_has_no_tools():
+    """Test that TitleGenerationAgent has no tools configured."""
+    agent = TitleGenerationAgent()
+
+    assert agent._function_toolset.tools == {}
+    assert not agent.get_tools()
+
+
+def test_title_generation_agent_instructions():
+    """Test that the agent instructions contain the system prompt."""
+    agent = TitleGenerationAgent()
+
+    # The agent should have the title generation system prompt as instructions
+    instructions = agent._instructions
+    assert len(instructions) == 1
+    expected = (
+        "You are a title generator. Your task is to create concise, descriptive titles "
+        "that accurately summarize conversation content and help the user quickly identify the "
+        "conversation.\n\n"
+    )
+    assert instructions[0] == expected

src/backend/chat/tests/tools/test_web_search_brave.py

@@ -38,9 +38,6 @@ def brave_settings(settings):
     settings.BRAVE_SEARCH_EXTRA_SNIPPETS = True
     settings.BRAVE_SUMMARIZATION_ENABLED = False
     settings.BRAVE_CACHE_TTL = 3600
-    settings.RAG_DOCUMENT_SEARCH_BACKEND = (
-        "chat.agent_rag.document_rag_backends.albert_rag_backend.AlbertRagBackend"
-    )
     settings.BRAVE_RAG_WEB_SEARCH_CHUNK_NUMBER = 5
 
 

src/backend/chat/tests/views/chat/conftest.py

@@ -0,0 +1,17 @@
+"""Common test fixtures for chat views tests."""
+
+from unittest import mock
+
+import pytest
+
+
+@pytest.fixture(autouse=True)
+def mock_process_request():
+    """
+    Mock process_request to bypass OIDC authentication in tests.
+    """
+    with mock.patch(
+        "lasuite.oidc_login.decorators.RefreshOIDCAccessToken.process_request"
+    ) as mocked_process_request:
+        mocked_process_request.return_value = None
+        yield mocked_process_request

src/backend/chat/tests/views/chat/conversations/conftest.py

@@ -1,5 +1,6 @@
 """Common test fixtures for chat conversation endpoint tests."""
 
+import asyncio
 import json
 
 from django.utils import timezone
@@ -10,15 +11,9 @@ import respx
 from freezegun import freeze_time
 
 
-@pytest.fixture(name="mock_openai_stream")
-@freeze_time("2025-07-25T10:36:35.297675Z")
-def fixture_mock_openai_stream():
-    """
-    Fixture to mock the OpenAI stream response.
-
-    See https://platform.openai.com/docs/api-reference/chat-streaming/streaming
-    """
-    openai_stream = (
+def _create_openai_stream_data():
+    """Helper to create OpenAI stream data."""
+    return (
         "data: "
         + json.dumps(
             {
@@ -59,12 +54,111 @@ def fixture_mock_openai_stream():
         "data: [DONE]\n\n"
     )
 
+
+def _create_mock_openai_route(with_delays: bool = False, delay_seconds: float = 1.0):
+    """Create a mock OpenAI stream route with optional delays."""
+    openai_stream = _create_openai_stream_data()
+
     async def mock_stream():
-        for line in openai_stream.splitlines(keepends=True):
+        lines = openai_stream.splitlines(keepends=True)
+        for i, line in enumerate(lines):
             yield line.encode()
+            if with_delays and i == 1:
+                # Delay after second line to trigger keepalive during streaming
+                await asyncio.sleep(delay_seconds)
+
+    return respx.post("https://www.external-ai-service.com/chat/completions").mock(
+        return_value=httpx.Response(200, stream=mock_stream())
+    )
+
+
+@pytest.fixture(name="mock_openai_stream")
+@freeze_time("2025-07-25T10:36:35.297675Z")
+def fixture_mock_openai_stream():
+    """
+    Fixture to mock the OpenAI stream response (no delays).
+
+    See https://platform.openai.com/docs/api-reference/chat-streaming/streaming
+    """
+    return _create_mock_openai_route(with_delays=False)
+
+
+@pytest.fixture(name="mock_openai_stream_slow")
+def fixture_mock_openai_stream_slow():
+    """
+    Fixture to mock the OpenAI stream response with delays to trigger keepalives.
+
+    No @freeze_time decorator because asyncio.sleep() needs real time to work properly.
+    """
+    return _create_mock_openai_route(with_delays=True, delay_seconds=1.0)
+
+
+@pytest.fixture(name="mock_openai_stream_with_title_generation")
+@freeze_time("2025-07-25T10:36:35.297675Z")
+def fixture_mock_openai_stream_with_title_generation():
+    """
+    Fixture to mock the OpenAI stream response.
+
+
+    This fixture handles two different types of API calls made during a single request:
+
+    1. **Conversation (streaming)**: The main chat uses `stream=True` to get real-time
+       token-by-token responses. The API returns chunked data like:
+       `data: {"choices": [{"delta": {"content": "Hello"}}]}`
+
+    2. **Title generation (non-streaming)**: After the conversation, the backend calls
+       the API again with `stream=False` to generate a title. This returns a standard
+       JSON response with the complete message.
+
+    The `handle_request` function inspects each incoming request's body to determine
+    which type of response to return:
+    - `{"stream": true, ...}`  → SSE streaming response
+    - `{"stream": false, ...}` → JSON response with generated title
+    Each call gets a new generator instance (avoiding generator exhaustion)
+    """
+
+    def create_stream_response():
+        """Create a fresh streaming response for each call."""
+        openai_stream = _create_openai_stream_data()
+
+        async def mock_stream():
+            for line in openai_stream.splitlines(keepends=True):
+                yield line.encode()
+
+        return httpx.Response(200, stream=mock_stream())
+
+    def create_non_stream_response():
+        """Create a non-streaming response for title generation."""
+        return httpx.Response(
+            200,
+            json={
+                "id": "chatcmpl-title",
+                "object": "chat.completion",
+                "created": int(timezone.make_naive(timezone.now()).timestamp()),
+                "model": "test-model",
+                "choices": [
+                    {
+                        "index": 0,
+                        "message": {
+                            "role": "assistant",
+                            "content": "GENERATED TITLE",
+                        },
+                        "finish_reason": "stop",
+                    }
+                ],
+                "usage": {"prompt_tokens": 50, "completion_tokens": 5, "total_tokens": 55},
+            },
+        )
+
+    def handle_request(request):
+        """Route to streaming or non-streaming response based on request."""
+        body = json.loads(request.content)
+        if body.get("stream", False):
+            return create_stream_response()
+        return create_non_stream_response()
 
     route = respx.post("https://www.external-ai-service.com/chat/completions").mock(
-        return_value=httpx.Response(200, stream=mock_stream())
+        side_effect=handle_request
     )
 
     return route

src/backend/chat/tests/views/chat/conversations/test_conversation.py

@@ -3,6 +3,7 @@
 
 import json
 import logging
+from unittest.mock import ANY, patch
 
 from django.utils import timezone
 
@@ -221,6 +222,133 @@ def test_post_conversation_data_protocol(api_client, mock_openai_stream):
     ]
 
 
+@freeze_time("2025-07-25T10:36:35.297675Z")
+@respx.mock
+@patch("chat.keepalive.get_current_time")
+def test_post_conversation_data_protocol_triggers_keepalives(
+    mock_time, api_client, mock_openai_stream
+):
+    """Test streaming response contains keepalive messages"""
+    chat_conversation = ChatConversationFactory(owner__language="en-us")
+    mock_time.side_effect = [float(i * 60) for i in range(10)]
+    url = f"/api/v1.0/chats/{chat_conversation.pk}/conversation/?protocol=data"
+    data = {
+        "messages": [
+            {
+                "id": "yuPoOuBkKA4FnKvk",
+                "role": "user",
+                "parts": [{"text": "Hello", "type": "text"}],
+                "content": "Hello",
+                "createdAt": "2025-07-03T15:22:17.105Z",
+            }
+        ]
+    }
+    api_client.force_login(chat_conversation.owner)
+
+    response = api_client.post(url, data, format="json")
+
+    assert response.status_code == status.HTTP_200_OK
+    assert response.get("Content-Type") == "text/event-stream"
+    assert response.get("x-vercel-ai-data-stream") == "v1"
+    assert response.streaming
+
+    # Wait for the streaming content to be fully received
+    response_content = b"".join(response.streaming_content).decode("utf-8")
+
+    # Replace UUIDs with placeholders for assertion
+    response_content = replace_uuids_with_placeholder(response_content)
+
+    assert response_content == (
+        '0:"Hello"\n'
+        '0:" there"\n'
+        'f:{"messageId":"<mocked_uuid>"}\n'
+        'd:{"finishReason":"stop","usage":{"promptTokens":0,"completionTokens":0}}\n'
+        '2:[{"status": "WAITING"}]\n'
+    )
+
+    assert mock_openai_stream.called
+
+    chat_conversation.refresh_from_db()
+    assert chat_conversation.ui_messages == [
+        {
+            "content": "Hello",
+            "createdAt": "2025-07-03T15:22:17.105Z",
+            "id": "yuPoOuBkKA4FnKvk",
+            "parts": [{"text": "Hello", "type": "text"}],
+            "role": "user",
+        }
+    ]
+
+    assert len(chat_conversation.messages) == 2
+
+    assert chat_conversation.messages[0].id == IsUUID(4)
+    assert chat_conversation.messages[0] == UIMessage(
+        id=chat_conversation.messages[0].id,  # don't test the message ID here
+        createdAt=timezone.now(),  # Mocked timestamp
+        content="Hello",
+        reasoning=None,
+        experimental_attachments=None,
+        role="user",
+        annotations=None,
+        toolInvocations=None,
+        parts=[TextUIPart(type="text", text="Hello")],
+    )
+
+    assert chat_conversation.messages[1].id == IsUUID(4)
+    assert chat_conversation.messages[1] == UIMessage(
+        id=chat_conversation.messages[1].id,  # don't test the message ID here
+        createdAt=timezone.now(),  # Mocked timestamp
+        content="Hello there",
+        reasoning=None,
+        experimental_attachments=None,
+        role="assistant",
+        annotations=None,
+        toolInvocations=None,
+        parts=[TextUIPart(type="text", text="Hello there")],
+    )
+
+    _run_id = chat_conversation.pydantic_messages[0]["run_id"]
+    assert chat_conversation.pydantic_messages == [
+        {
+            "instructions": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\n"
+                "Answer in english."
+            ),
+            "kind": "request",
+            "parts": [
+                {
+                    "content": ["Hello"],
+                    "part_kind": "user-prompt",
+                    "timestamp": "2025-07-25T10:36:35.297675Z",
+                },
+            ],
+            "run_id": _run_id,
+        },
+        {
+            "finish_reason": "stop",
+            "kind": "response",
+            "model_name": "test-model",
+            "parts": [{"content": "Hello there", "id": None, "part_kind": "text"}],
+            "provider_details": {"finish_reason": "stop"},
+            "provider_name": "openai",
+            "provider_response_id": "chatcmpl-1234567890",
+            "timestamp": "2025-07-25T10:36:35.297675Z",
+            "usage": {
+                "cache_audio_read_tokens": 0,
+                "cache_read_tokens": 0,
+                "cache_write_tokens": 0,
+                "details": {},
+                "input_audio_tokens": 0,
+                "input_tokens": 0,
+                "output_audio_tokens": 0,
+                "output_tokens": 0,
+            },
+            "run_id": _run_id,
+        },
+    ]
+
+
 @freeze_time("2025-07-25T10:36:35.297675Z")
 @respx.mock
 def test_post_conversation_text_protocol(api_client, mock_openai_stream):
@@ -1344,3 +1472,143 @@ async def test_post_conversation_async(api_client, mock_openai_stream, monkeypat
             "run_id": _run_id,
         },
     ]
+
+
+@freeze_time("2025-07-25T10:36:35.297675Z", tick=True)
+@respx.mock
+@pytest.mark.asyncio
+async def test_post_conversation_async_triggers_keepalive(
+    api_client, mock_openai_stream_slow, monkeypatch, caplog, settings
+):
+    """Test posting messages to a conversation using the 'data' protocol."""
+    monkeypatch.setenv("PYTHON_SERVER_MODE", "async")
+
+    settings.KEEPALIVE_INTERVAL = 1  # s
+
+    chat_conversation = await sync_to_async(ChatConversationFactory)(owner__language="en-us")
+
+    url = f"/api/v1.0/chats/{chat_conversation.pk}/conversation/?protocol=data"
+    data = {
+        "messages": [
+            {
+                "id": "yuPoOuBkKA4FnKvk",
+                "role": "user",
+                "parts": [{"text": "Hello", "type": "text"}],
+                "content": "Hello",
+                "createdAt": "2025-07-03T15:22:17.105Z",
+            }
+        ]
+    }
+    await api_client.aforce_login(chat_conversation.owner)
+
+    caplog.clear()
+    caplog.set_level(level=logging.DEBUG, logger="chat.views")
+
+    response = await sync_to_async(api_client.post)(url, data, format="json")  # client is sync
+
+    assert response.status_code == status.HTTP_200_OK
+    assert response.get("Content-Type") == "text/event-stream"
+    assert response.get("x-vercel-ai-data-stream") == "v1"
+    assert response.streaming
+
+    assert "Using ASYNC streaming for chat conversation" in caplog.text
+
+    # Wait for the streaming content to be fully received => async iterator -> list
+    # This fails it the streaming is not an async generator
+    response_content = b"".join([content async for content in response.streaming_content]).decode(
+        "utf-8"
+    )
+
+    # Replace UUIDs with placeholders for assertion
+    response_content = replace_uuids_with_placeholder(response_content)
+
+    assert response_content == (
+        '0:"Hello"\n'
+        '2:[{"status": "WAITING"}]\n'
+        '0:" there"\n'
+        'f:{"messageId":"<mocked_uuid>"}\n'
+        'd:{"finishReason":"stop","usage":{"promptTokens":0,"completionTokens":0}}\n'
+    )
+
+    assert mock_openai_stream_slow.called
+
+    await chat_conversation.arefresh_from_db()
+    assert chat_conversation.ui_messages == [
+        {
+            "content": "Hello",
+            "createdAt": "2025-07-03T15:22:17.105Z",
+            "id": "yuPoOuBkKA4FnKvk",
+            "parts": [{"text": "Hello", "type": "text"}],
+            "role": "user",
+        }
+    ]
+
+    assert len(chat_conversation.messages) == 2
+
+    assert chat_conversation.messages[0].id == IsUUID(4)
+    assert chat_conversation.messages[0] == UIMessage(
+        id=chat_conversation.messages[0].id,  # don't test the message ID here
+        createdAt=chat_conversation.messages[0].createdAt,  # Mocked timestamp
+        content="Hello",
+        reasoning=None,
+        experimental_attachments=None,
+        role="user",
+        annotations=None,
+        toolInvocations=None,
+        parts=[TextUIPart(type="text", text="Hello")],
+    )
+
+    assert chat_conversation.messages[1].id == IsUUID(4)
+    assert chat_conversation.messages[1] == UIMessage(
+        id=chat_conversation.messages[1].id,  # don't test the message ID here
+        createdAt=chat_conversation.messages[1].createdAt,  # Mocked timestamp
+        content="Hello there",
+        reasoning=None,
+        experimental_attachments=None,
+        role="assistant",
+        annotations=None,
+        toolInvocations=None,
+        parts=[TextUIPart(type="text", text="Hello there")],
+    )
+
+    _run_id = chat_conversation.pydantic_messages[0]["run_id"]
+
+    # using ANY because time is not frozen in this api mock
+    assert chat_conversation.pydantic_messages == [
+        {
+            "instructions": (
+                "You are a helpful test assistant :)\n\n"
+                "Today is Friday 25/07/2025.\n\nAnswer in english."
+            ),
+            "kind": "request",
+            "parts": [
+                {
+                    "content": ["Hello"],
+                    "part_kind": "user-prompt",
+                    "timestamp": ANY,
+                },
+            ],
+            "run_id": _run_id,
+        },
+        {
+            "finish_reason": "stop",
+            "kind": "response",
+            "model_name": "test-model",
+            "parts": [{"content": "Hello there", "id": None, "part_kind": "text"}],
+            "provider_details": {"finish_reason": "stop"},
+            "provider_name": "openai",
+            "provider_response_id": "chatcmpl-1234567890",
+            "timestamp": ANY,
+            "usage": {
+                "cache_audio_read_tokens": 0,
+                "cache_read_tokens": 0,
+                "cache_write_tokens": 0,
+                "details": {},
+                "input_audio_tokens": 0,
+                "input_tokens": 0,
+                "output_audio_tokens": 0,
+                "output_tokens": 0,
+            },
+            "run_id": _run_id,
+        },
+    ]

src/backend/chat/tests/views/chat/conversations/test_conversation_with_document_upload.py

@@ -8,6 +8,7 @@ import logging
 from io import BytesIO
 from unittest import mock
 
+from django.contrib.sessions.backends.cache import SessionStore
 from django.utils import formats, timezone
 
 import httpx
@@ -41,28 +42,49 @@ from chat.tests.utils import replace_uuids_with_placeholder
 pytestmark = pytest.mark.django_db(transaction=True)
 
 
-@pytest.fixture(autouse=True)
-def ai_settings(settings):
+@pytest.fixture(
+    autouse=True,
+    params=[
+        "chat.agent_rag.document_rag_backends.find_rag_backend.FindRagBackend",
+        "chat.agent_rag.document_rag_backends.albert_rag_backend.AlbertRagBackend",
+    ],
+)
+def ai_settings(request, settings):
     """Fixture to set AI service URLs for testing."""
-    settings.AI_BASE_URL = "https://www.external-ai-service.com/"
-    settings.AI_API_KEY = "test-api-key"
-    settings.AI_MODEL = "test-model"
-    settings.AI_AGENT_INSTRUCTIONS = "You are a helpful test assistant :)"
 
-    # Enable Albert API for document search
-    settings.RAG_DOCUMENT_SEARCH_BACKEND = (
-        "chat.agent_rag.document_rag_backends.albert_rag_backend.AlbertRagBackend"
-    )
-    settings.ALBERT_API_URL = "https://albert.api.etalab.gouv.fr"
-    settings.ALBERT_API_KEY = "albert-api-key"
+    # enable on rag document search tool
+    settings.RAG_DOCUMENT_SEARCH_BACKEND = request.param
     settings.RAG_WEB_SEARCH_PROMPT_UPDATE = (
         "Based on the following document contents:\n\n{search_results}\n\n"
         "Please answer the user's question: {user_prompt}"
     )
 
+    settings.AI_BASE_URL = "https://www.external-ai-service.com/"
+    settings.AI_API_KEY = "test-api-key"
+    settings.AI_MODEL = "test-model"
+    settings.AI_AGENT_INSTRUCTIONS = "You are a helpful test assistant :)"
+
+    # Albert API settings
+    settings.ALBERT_API_URL = "https://albert.api.etalab.gouv.fr"
+    settings.ALBERT_API_KEY = "albert-api-key"
+
+    # Find API settings
+    settings.FIND_API_URL = "https://find.api.example.com"
+    settings.FIND_API_KEY = "find-api-key"
+
     return settings
 
 
+@pytest.fixture(autouse=True)
+def mock_refresh_access_token():
+    """Mock refresh_access_token to bypass token refresh in tests."""
+    with mock.patch("utils.oidc.refresh_access_token") as mocked_refresh_access_token:
+        session = SessionStore()
+        session["oidc_access_token"] = "mocked-access-token"
+        mocked_refresh_access_token.return_value = session
+        yield mocked_refresh_access_token
+
+
 @pytest.fixture(name="sample_pdf_content")
 def fixture_sample_pdf_content():
     """Create a dummy PDF content as BytesIO."""
@@ -81,10 +103,18 @@ def fixture_sample_pdf_content():
     return BytesIO(pdf_data)
 
 
-@pytest.fixture(name="mock_albert_api")
-def fixture_mock_albert_api():
+@pytest.fixture(name="mock_document_api")
+def fixture_mock_document_api():
     """Fixture to mock the Albert API endpoints."""
     # Mock collection creation
+
+    document_name = "sample.pdf"
+    document_content = "This is the content of the PDF."
+    prompt_tokens = 10
+    completion_tokens = 20
+    search_method = "semantic"
+    search_score = 0.9
+
     responses.post(
         "https://albert.api.etalab.gouv.fr/v1/collections",
         json={"id": "123", "name": "test-collection"},
@@ -101,7 +131,7 @@ def fixture_mock_albert_api():
                     "metadata": {"document_name": "sample.pdf"},
                 }
             ],
-            "usage": {"prompt_tokens": 10, "completion_tokens": 20},
+            "usage": {"prompt_tokens": prompt_tokens, "completion_tokens": completion_tokens},
         },
         status=status.HTTP_200_OK,
     )
@@ -119,20 +149,42 @@ def fixture_mock_albert_api():
         json={
             "data": [
                 {
-                    "method": "semantic",
+                    "method": search_method,
                     "chunk": {
                         "id": 123,
-                        "content": "This is the content of the PDF.",
-                        "metadata": {"document_name": "sample.pdf"},
+                        "content": document_content,
+                        "metadata": {"document_name": document_name},
                     },
-                    "score": 0.9,
+                    "score": search_score,
                 }
             ],
-            "usage": {"prompt_tokens": 10, "completion_tokens": 20},
+            "usage": {"prompt_tokens": prompt_tokens, "completion_tokens": completion_tokens},
         },
         status=status.HTTP_200_OK,
     )
 
+    # Mock document indexing (Find API)
+    responses.post(
+        "https://find.api.example.com/api/v1.0/documents/index/",
+        json={"id": "456", "status": "indexed"},
+        status=status.HTTP_200_OK,
+    )
+
+    # Mock document search (Find API)
+    responses.post(
+        "https://find.api.example.com/api/v1.0/documents/search/",
+        json=[
+            {
+                "_source": {
+                    "title.fr": document_name,
+                    "content.fr": document_content,
+                },
+                "_score": search_score,
+            }
+        ],
+        status=status.HTTP_200_OK,
+    )
+
 
 @pytest.fixture(name="mock_summarization_agent")
 def fixture_mock_summarization_agent():
@@ -219,7 +271,7 @@ def fixture_mock_openai_stream():
 def test_post_conversation_with_document_upload(
     # pylint: disable=too-many-arguments,too-many-positional-arguments
     api_client,
-    mock_albert_api,  # pylint: disable=unused-argument
+    mock_document_api,  # pylint: disable=unused-argument
     sample_pdf_content,
     today_promt_date,
     mock_ai_agent_service,
@@ -548,7 +600,7 @@ def test_post_conversation_with_document_upload_feature_disabled(
 @freeze_time()
 def test_post_conversation_with_document_upload_summarize(  # pylint: disable=too-many-arguments,too-many-positional-arguments  # noqa: PLR0913
     api_client,
-    mock_albert_api,  # pylint: disable=unused-argument
+    mock_document_api,  # pylint: disable=unused-argument
     sample_pdf_content,
     today_promt_date,
     mock_ai_agent_service,

src/backend/chat/tests/views/chat/conversations/test_conversation_with_document_url.py

@@ -37,11 +37,19 @@ from chat.tests.utils import replace_uuids_with_placeholder
 pytestmark = pytest.mark.django_db(transaction=True)
 
 
-@pytest.fixture(autouse=True)
-def ai_settings(settings):
+@pytest.fixture(
+    autouse=True,
+    params=[
+        "chat.agent_rag.document_rag_backends.find_rag_backend.FindRagBackend",
+        "chat.agent_rag.document_rag_backends.albert_rag_backend.AlbertRagBackend",
+    ],
+)
+def ai_settings(request, settings):
     """Fixture to set AI service URLs for testing."""
+    settings.RAG_DOCUMENT_SEARCH_BACKEND = request.param
     settings.AI_BASE_URL = "https://www.external-ai-service.com/"
     settings.AI_API_KEY = "test-api-key"
+    settings.FIND_API_KEY = "find-api-key"
     settings.AI_MODEL = "test-model"
     settings.AI_AGENT_INSTRUCTIONS = "You are a helpful test assistant :)"
     return settings
@@ -85,6 +93,10 @@ def test_post_conversation_with_local_pdf_document_url(
         json={"id": "document_id", "object": "document"},
         status=200,
     )
+    responses.post(
+        "https://app-find/api/v1.0/documents/index/",
+        status=200,
+    )
 
     chat_conversation = ChatConversationFactory(owner__language="en-us")
     api_client.force_authenticate(user=chat_conversation.owner)
@@ -120,29 +132,28 @@ def test_post_conversation_with_local_pdf_document_url(
     )
 
     async def agent_model(messages: list[ModelMessage], _info: AgentInfo):
-        presigned_url = messages[0].parts[0].content[1].url
-        assert presigned_url.startswith("http://localhost:9000/conversations-media-storage/")
-        assert presigned_url.find("X-Amz-Signature=") != -1
-        assert presigned_url.find("X-Amz-Date=") != -1
-        assert presigned_url.find("X-Amz-Expires=") != -1
-
         assert messages == [
             ModelRequest(
                 parts=[
-                    UserPromptPart(
-                        content=[
-                            "What is in this document?",
-                            DocumentUrl(
-                                url=presigned_url,  # presigned URL for this conversation
-                                media_type="application/pdf",
-                                identifier="sample.pdf",
-                            ),
-                        ],
-                        timestamp=timezone.now(),
-                    ),
+                    UserPromptPart(content=["What is in this document?"], timestamp=timezone.now())
                 ],
-                instructions=f"You are a helpful test assistant :)\n\n{today_promt_date}"
-                "\n\nAnswer in english.",
+                instructions=(
+                    "You are a helpful test assistant :)\n\n"
+                    f"{today_promt_date}\n\n"
+                    "Answer in english.\n\n"
+                    "Use document_search_rag ONLY to retrieve specific passages from attached "
+                    "documents. Do NOT use it to summarize; for summaries, call the summarize "
+                    "tool instead.\n\nWhen you receive a result from the summarization tool, "
+                    "you MUST return it directly to the user without any modification, "
+                    "paraphrasing, or additional summarization.The tool already produces "
+                    "optimized summaries that should be presented verbatim.You may translate "
+                    "the summary if required, but you MUST preserve all the information from "
+                    "the original summary.You may add a follow-up question after the summary "
+                    "if needed.\n\n"
+                    "[Internal context] User documents are attached to this conversation. "
+                    "Do not request re-upload of documents; consider them already available "
+                    "via the internal store."
+                ),
                 run_id=messages[0].run_id,
             )
         ]
@@ -186,9 +197,7 @@ def test_post_conversation_with_local_pdf_document_url(
         createdAt=timezone.now(),
         content="What is in this document?",
         reasoning=None,
-        experimental_attachments=[
-            Attachment(name="sample.pdf", contentType="application/pdf", url=document_url)
-        ],
+        experimental_attachments=None,  # We should fix this, but for now document appears in source
         role="user",
         annotations=None,
         toolInvocations=None,
@@ -220,20 +229,29 @@ def test_post_conversation_with_local_pdf_document_url(
         {
             "instructions": "You are a helpful test assistant :)\n\n"
             f"{today_promt_date}\n\n"
-            "Answer in english.",
+            "Answer in english.\n"
+            "\n"
+            "Use document_search_rag ONLY to retrieve specific passages "
+            "from attached documents. Do NOT use it to summarize; for "
+            "summaries, call the summarize tool instead.\n"
+            "\n"
+            "When you receive a result from the summarization tool, you "
+            "MUST return it directly to the user without any "
+            "modification, paraphrasing, or additional summarization.The "
+            "tool already produces optimized summaries that should be "
+            "presented verbatim.You may translate the summary if "
+            "required, but you MUST preserve all the information from "
+            "the original summary.You may add a follow-up question after "
+            "the summary if needed.\n"
+            "\n"
+            "[Internal context] User documents are attached to this "
+            "conversation. Do not request re-upload of documents; "
+            "consider them already available via the internal store.",
             "kind": "request",
             "parts": [
                 {
                     "content": [
                         "What is in this document?",
-                        {
-                            "force_download": False,
-                            "identifier": "sample.pdf",
-                            "kind": "document-url",
-                            "media_type": "application/pdf",
-                            "url": document_url,
-                            "vendor_metadata": None,
-                        },
                     ],
                     "part_kind": "user-prompt",
                     "timestamp": timestamp,
@@ -795,6 +813,10 @@ def test_post_conversation_with_local_not_pdf_document_url(
         json={"id": "document_id", "object": "document"},
         status=200,
     )
+    responses.post(
+        "https://app-find/api/v1.0/documents/index/",
+        status=200,
+    )
 
     chat_conversation = ChatConversationFactory(owner__language="en-us")
     api_client.force_authenticate(user=chat_conversation.owner)

src/backend/chat/tests/views/chat/conversations/test_conversation_with_history.py

@@ -2,6 +2,7 @@
 # pylint: disable=too-many-lines
 
 import json
+from unittest.mock import patch
 
 from django.utils import timezone
 
@@ -11,6 +12,7 @@ from dirty_equals import IsUUID
 from freezegun import freeze_time
 from rest_framework import status
 
+from chat.agents.conversation import TitleGenerationAgent
 from chat.ai_sdk_types import (
     Attachment,
     TextUIPart,
@@ -35,6 +37,7 @@ def ai_settings(settings):
     settings.AI_MODEL = "test-model"
     settings.AI_AGENT_INSTRUCTIONS = "You are a helpful test assistant :)"
 
+    settings.AUTO_TITLE_AFTER_USER_MESSAGES = None  # disable auto title generation
     return settings
 
 
@@ -1573,3 +1576,307 @@ def test_post_conversation_add_image_to_conversation_with_tool_history(
         toolInvocations=None,
         parts=[TextUIPart(type="text", text="I see a cat in the picture.")],
     )
+
+
+@freeze_time("2025-07-25T10:36:35.297675Z")
+@respx.mock
+@patch("chat.clients.pydantic_ai.TitleGenerationAgent", wraps=TitleGenerationAgent)
+def test_post_conversation_triggers_automatic_title_generation_after_first_message(
+    mock_title_agent, api_client, mock_openai_stream_with_title_generation, settings
+):
+    """
+    Test that posting the first user message triggers automatic title generation.
+
+    AUTO_TITLE_AFTER_USER_MESSAGES = 1
+
+    The conversation is a new one. Posting the first message
+    should trigger title generation via the TitleGenerationAgent.
+    """
+    # Configure the title generation threshold
+    settings.AUTO_TITLE_AFTER_USER_MESSAGES = 1
+    conversation = ChatConversationFactory()
+    url = f"/api/v1.0/chats/{conversation.pk}/conversation/?protocol=data"
+    data = {
+        "messages": [
+            {
+                "id": "third-user-msg",
+                "role": "user",
+                "parts": [{"text": "Can you explain backpropagation?", "type": "text"}],
+                "content": "Can you explain backpropagation?",
+                "createdAt": "2025-07-25T10:36:00.000Z",
+            }
+        ]
+    }
+    api_client.force_login(conversation.owner)
+
+    conversation.title = "initial title"
+    conversation.save()
+
+    assert not conversation.title_set_by_user_at
+
+    response = api_client.post(url, data, format="json")
+
+    assert response.status_code == status.HTTP_200_OK
+    assert response.get("Content-Type") == "text/event-stream"
+    assert response.streaming
+
+    # Wait for the streaming content to be fully received
+    response_content = b"".join(response.streaming_content).decode("utf-8")
+
+    # Verify the conversation_metadata event is in the stream
+
+    assert '"type": "conversation_metadata"' in response_content
+
+    # Refresh and verify title was updated
+    conversation.refresh_from_db()
+
+    assert conversation.title == "GENERATED TITLE"
+    # title_set_by_user_at should remain None since it was auto-generated
+    assert not conversation.title_set_by_user_at
+
+    assert mock_openai_stream_with_title_generation.called
+    assert mock_openai_stream_with_title_generation.call_count == 2
+
+    # Verify TitleGenerationAgent was called
+    mock_title_agent.assert_called_once()
+
+
+@freeze_time("2025-07-25T10:36:35.297675Z")
+@respx.mock
+def test_post_conversation_triggers_automatic_title_generation_at_threshold(
+    api_client, mock_openai_stream_with_title_generation, settings, history_conversation
+):
+    """
+    Test that posting the 3rd user message triggers automatic title generation.
+
+    AUTO_TITLE_AFTER_USER_MESSAGES = 3
+
+
+    The history_conversation fixture has 2 user messages. Posting a 3rd message
+    should trigger title generation via the TitleGenerationAgent.
+    """
+    # Configure the title generation threshold
+    settings.AUTO_TITLE_AFTER_USER_MESSAGES = 3
+
+    url = f"/api/v1.0/chats/{history_conversation.pk}/conversation/?protocol=data"
+    data = {
+        "messages": [
+            {
+                "id": "third-user-msg",
+                "role": "user",
+                "parts": [{"text": "Can you explain backpropagation?", "type": "text"}],
+                "content": "Can you explain backpropagation?",
+                "createdAt": "2025-07-25T10:36:00.000Z",
+            }
+        ]
+    }
+    api_client.force_login(history_conversation.owner)
+
+    history_conversation.title = "initial title"
+    history_conversation.save()
+
+    assert not history_conversation.title_set_by_user_at
+
+    response = api_client.post(url, data, format="json")
+
+    assert response.status_code == status.HTTP_200_OK
+    assert response.get("Content-Type") == "text/event-stream"
+    assert response.streaming
+
+    # Wait for the streaming content to be fully received
+    response_content = b"".join(response.streaming_content).decode("utf-8")
+
+    # Verify the conversation_metadata event is in the stream
+
+    assert '"type": "conversation_metadata"' in response_content
+
+    # Refresh and verify title was updated
+    history_conversation.refresh_from_db()
+
+    assert history_conversation.title == "GENERATED TITLE"
+    # title_set_by_user_at should remain None since it was auto-generated
+    assert not history_conversation.title_set_by_user_at
+
+    assert mock_openai_stream_with_title_generation.called
+    assert mock_openai_stream_with_title_generation.call_count == 2
+
+
+@freeze_time("2025-07-25T10:36:35.297675Z")
+@respx.mock
+def test_post_conversation_does_not_regenerate_title_when_user_set(
+    api_client, mock_openai_stream_with_title_generation, settings, history_conversation
+):
+    """
+    Test that title is NOT regenerated if the user has manually set a title.
+    """
+    settings.AUTO_TITLE_AFTER_USER_MESSAGES = 3
+
+    # Simulate user having set a custom title
+    history_conversation.title = "My Custom Title"
+    history_conversation.title_set_by_user_at = timezone.now()
+    history_conversation.save()
+
+    url = f"/api/v1.0/chats/{history_conversation.pk}/conversation/?protocol=data"
+    data = {
+        "messages": [
+            {
+                "id": "third-user-msg",
+                "role": "user",
+                "parts": [{"text": "Can you explain backpropagation?", "type": "text"}],
+                "content": "Can you explain backpropagation?",
+                "createdAt": "2025-07-25T10:36:00.000Z",
+            }
+        ]
+    }
+    api_client.force_login(history_conversation.owner)
+
+    response = api_client.post(url, data, format="json")
+
+    assert response.status_code == status.HTTP_200_OK
+
+    # Consume the stream
+    response_content = b"".join(response.streaming_content).decode("utf-8")
+
+    # conversation_metadata should NOT be in the stream since title wasn't generated
+    assert "conversation_metadata" not in response_content
+
+    # Refresh and verify title was NOT changed
+    history_conversation.refresh_from_db()
+
+    assert history_conversation.title == "My Custom Title"
+    assert history_conversation.title_set_by_user_at
+
+    assert mock_openai_stream_with_title_generation.called
+    assert mock_openai_stream_with_title_generation.call_count == 1
+
+
+@freeze_time("2025-07-25T10:36:35.297675Z")
+@respx.mock
+def test_post_conversation_does_not_generate_title_before_threshold(
+    api_client, mock_openai_stream_with_title_generation, settings
+):
+    """
+    Test that title is NOT generated before reaching the message threshold.
+    """
+    settings.AUTO_TITLE_AFTER_USER_MESSAGES = 3
+
+    # Create a conversation with only 1 user message
+    history_timestamp = timezone.now().replace(year=2025, month=6, day=15, hour=10, minute=30)
+    conversation = ChatConversationFactory(title="initial title")
+
+    conversation.messages = [
+        UIMessage(
+            id="prev-user-msg-1",
+            createdAt=history_timestamp,
+            content="Hello!",
+            reasoning=None,
+            experimental_attachments=None,
+            role="user",
+            annotations=None,
+            toolInvocations=None,
+            parts=[TextUIPart(type="text", text="Hello!")],
+        ),
+        UIMessage(
+            id="prev-assistant-msg-1",
+            createdAt=history_timestamp.replace(minute=31),
+            content="Hi there! How can I help you?",
+            reasoning=None,
+            experimental_attachments=None,
+            role="assistant",
+            annotations=None,
+            toolInvocations=None,
+            parts=[TextUIPart(type="text", text="Hi there! How can I help you?")],
+        ),
+    ]
+    conversation.save()
+
+    url = f"/api/v1.0/chats/{conversation.pk}/conversation/?protocol=data"
+    data = {
+        "messages": [
+            {
+                "id": "second-user-msg",
+                "role": "user",
+                "parts": [{"text": "What's machine learning?", "type": "text"}],
+                "content": "What's machine learning?",
+                "createdAt": "2025-07-25T10:36:00.000Z",
+            }
+        ]
+    }
+    api_client.force_login(conversation.owner)
+
+    response = api_client.post(url, data, format="json")
+
+    assert response.status_code == status.HTTP_200_OK
+
+    # Consume the stream
+    response_content = b"".join(response.streaming_content).decode("utf-8")
+
+    # conversation_metadata should NOT be in the stream (only 2 user messages)
+    assert "conversation_metadata" not in response_content
+
+    # Refresh and verify title was not updated
+    conversation.refresh_from_db()
+
+    assert conversation.title == "initial title"
+    assert not conversation.title_set_by_user_at
+
+    assert mock_openai_stream_with_title_generation.call_count == 1
+
+
+@freeze_time("2025-07-25T10:36:35.297675Z")
+@respx.mock
+def test_post_conversation_does_not_generate_title_after_threshold(
+    api_client, mock_openai_stream_with_title_generation, settings, history_conversation
+):
+    """
+    Test that posting the 3rd user message does not trigger automatic title generation.
+
+    AUTO_TITLE_AFTER_USER_MESSAGES = 2
+
+    The history_conversation fixture has 2 user messages. Posting a 3rd message
+    should not trigger title generation.
+    """
+    # Configure the title generation threshold
+    settings.AUTO_TITLE_AFTER_USER_MESSAGES = 2
+
+    url = f"/api/v1.0/chats/{history_conversation.pk}/conversation/?protocol=data"
+    data = {
+        "messages": [
+            {
+                "id": "third-user-msg",
+                "role": "user",
+                "parts": [{"text": "Can you explain backpropagation?", "type": "text"}],
+                "content": "Can you explain backpropagation?",
+                "createdAt": "2025-07-25T10:36:00.000Z",
+            }
+        ]
+    }
+    api_client.force_login(history_conversation.owner)
+
+    history_conversation.title = "initial title"
+    history_conversation.save()
+
+    assert not history_conversation.title_set_by_user_at
+
+    response = api_client.post(url, data, format="json")
+
+    assert response.status_code == status.HTTP_200_OK
+    assert response.get("Content-Type") == "text/event-stream"
+    assert response.streaming
+
+    # Wait for the streaming content to be fully received
+    response_content = b"".join(response.streaming_content).decode("utf-8")
+
+    # Verify the conversation_metadata event is not in the stream
+
+    assert "conversation_metadata" not in response_content
+
+    # Refresh and verify title was NOT updated (past threshold)
+    history_conversation.refresh_from_db()
+
+    # title not updated
+    assert history_conversation.title == "initial title"
+    # title_set_by_user_at should remain None since it was auto-generated
+    assert not history_conversation.title_set_by_user_at
+
+    assert mock_openai_stream_with_title_generation.call_count == 1

src/backend/chat/tests/views/chat/test_create.py

@@ -28,6 +28,7 @@ def test_create_conversation(api_client):
     conversation = ChatConversation.objects.get(id=response.data["id"])
     assert conversation.owner == user
     assert conversation.title == "New Conversation"
+    assert not conversation.title_set_by_user_at
 
 
 def test_create_conversation_other_owner(api_client):

src/backend/chat/tests/views/chat/test_update.py

@@ -2,6 +2,7 @@
 
 import pytest
 from rest_framework import status
+from rest_framework.exceptions import ErrorDetail
 
 from core.factories import UserFactory
 
@@ -26,6 +27,34 @@ def test_update_conversation(api_client):
     # Verify in database
     conversation = ChatConversation.objects.get(id=chat_conversation.pk)
     assert conversation.title == "Updated Title"
+    assert conversation.title_set_by_user_at
+
+
+def test_update_conversation_limit_title_length(api_client):
+    """Test that updating a conversation with a title exceeding 100 characters fails validation."""
+    chat_conversation = ChatConversationFactory(title="Initial title")
+
+    url = f"/api/v1.0/chats/{chat_conversation.pk}/"
+    # Create a 101-character title to exceed the 100-character maximum limit
+    new_title = "X" * 101
+    data = {"title": new_title}
+    api_client.force_login(chat_conversation.owner)
+    response = api_client.put(url, data, format="json")
+
+    assert response.status_code == status.HTTP_400_BAD_REQUEST
+
+    assert response.data == {
+        "title": [
+            ErrorDetail(
+                string="Ensure this field has no more than 100 characters.", code="max_length"
+            )
+        ]
+    }
+
+    # Verify in database (title should remain unchanged)
+    conversation = ChatConversation.objects.get(id=chat_conversation.pk)
+    assert conversation.title == "Initial title"
+    assert not conversation.title_set_by_user_at
 
 
 def test_update_conversation_anonymous(api_client):

src/backend/chat/tools/data_analysis.py

@@ -1,873 +0,0 @@
-"""Data analysis tool for tabular files (CSV, Excel)."""
-
-import base64
-import functools
-import json
-import logging
-import uuid
-from io import BytesIO
-from typing import Any, Dict
-
-import matplotlib
-import numpy as np
-
-matplotlib.use("Agg")  # Use non-interactive backend
-import matplotlib.pyplot as plt
-import pandas as pd
-
-from django.conf import settings
-from django.core.files.storage import default_storage
-from django.db.models import Q
-from asgiref.sync import sync_to_async
-from pydantic_ai import Agent, RunContext
-from pydantic_ai.exceptions import ModelRetry
-from pydantic_ai.messages import ToolReturn
-
-from core.file_upload.enums import AttachmentStatus
-from core.file_upload.utils import generate_retrieve_policy
-
-from chat.agents.base import BaseAgent, prepare_custom_model
-from chat.models import ChatConversationAttachment
-from chat.tools.exceptions import ModelCannotRetry
-from chat.tools.utils import last_model_retry_soft_fail
-
-logger = logging.getLogger(__name__)
-
-# MIME types for tabular files
-TABULAR_MIME_TYPES = [
-    "text/csv",
-    "application/csv",
-    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
-    "application/vnd.ms-excel",
-    "application/excel",
-]
-
-
-@sync_to_async
-def read_tabular_file(attachment) -> bytes:
-    """Read tabular file content asynchronously."""
-    with default_storage.open(attachment.key, "rb") as f:
-        return f.read()
-
-
-def detect_csv_separator(file_data: bytes) -> str:
-    """
-    Detect the CSV separator by analyzing the first few lines.
-    
-    Returns the most likely separator: ',', ';', or '\t'
-    """
-    # Read first 10KB to analyze
-    sample = file_data[:10240].decode("utf-8", errors="ignore")
-    lines = sample.split("\n")[:10]  # First 10 lines
-    
-    if not lines:
-        return ","  # Default to comma
-    
-    # Count occurrences of each separator in the first few lines
-    comma_count = sum(line.count(",") for line in lines)
-    semicolon_count = sum(line.count(";") for line in lines)
-    tab_count = sum(line.count("\t") for line in lines)
-    
-    # Return the separator with the highest count
-    if tab_count > comma_count and tab_count > semicolon_count:
-        return "\t"
-    elif semicolon_count > comma_count:
-        return ";"
-    else:
-        return ","  # Default to comma
-
-
-def _convert_to_serializable(obj: Any) -> Any:
-    """
-    Convert pandas/numpy types to Python native types for JSON serialization.
-    
-    Handles:
-    - pandas DataFrame/Series
-    - numpy scalars (int64, float64, etc.)
-    - numpy arrays
-    - pandas Timestamp
-    - Other non-serializable types
-    
-    Args:
-        obj: The object to convert.
-        
-    Returns:
-        A JSON-serializable version of the object.
-    """
-    
-    # Handle pandas DataFrame
-    if isinstance(obj, pd.DataFrame):
-        # Limit number of rows to avoid huge responses
-        if len(obj) > 1000:
-            obj = obj.head(1000)
-            logger.warning("Result truncated to 1000 rows")
-        return obj.to_dict(orient="records")
-    
-    # Handle pandas Series
-    if isinstance(obj, pd.Series):
-        # Convert Series to dict, handling index
-        result_dict = obj.to_dict()
-        # Convert any numpy/pandas types in the values
-        return {str(k): _convert_to_serializable(v) for k, v in result_dict.items()}
-    
-    # Handle numpy scalars
-    if isinstance(obj, (np.integer, np.floating)):
-        return obj.item()  # Convert to Python native int/float
-    
-    # Handle numpy arrays
-    if isinstance(obj, np.ndarray):
-        return obj.tolist()
-    
-    # Handle pandas Timestamp
-    if isinstance(obj, pd.Timestamp):
-        return obj.isoformat()
-    
-    # Handle lists and tuples - recursively convert elements
-    if isinstance(obj, (list, tuple)):
-        return [_convert_to_serializable(item) for item in obj]
-    
-    # Handle dicts - recursively convert values
-    if isinstance(obj, dict):
-        return {str(k): _convert_to_serializable(v) for k, v in obj.items()}
-    
-    # Handle None, bool, int, float, str - these are already serializable
-    if obj is None or isinstance(obj, (bool, int, float, str)):
-        return obj
-    
-    # Fallback: try to convert to string
-    try:
-        return str(obj)
-    except Exception:
-        logger.warning("Could not serialize object of type %s, returning None", type(obj))
-        return None
-
-
-def _is_valid_excel_file(file_data: bytes, file_name: str) -> bool:
-    """
-    Check if the file data appears to be a valid Excel file.
-    
-    XLSX files are ZIP archives, so they should start with ZIP signature (PK\x03\x04).
-    XLS files have a different signature.
-    """
-    if not file_data:
-        return False
-    
-    file_lower = file_name.lower()
-    
-    # Check for XLSX (ZIP-based) signature
-    if file_lower.endswith((".xlsx", ".xlsm", ".xlsb")):
-        # XLSX files are ZIP archives, should start with PK\x03\x04
-        return file_data[:4] == b"PK\x03\x04"
-    
-    # Check for XLS (OLE2) signature
-    if file_lower.endswith(".xls"):
-        # XLS files are OLE2 compound documents, should start with specific signature
-        # Common signatures: 0xD0CF11E0 (OLE2) or 0x504B0304 (sometimes saved as ZIP)
-        return (
-            file_data[:4] == b"\xd0\xcf\x11\xe0"  # OLE2 signature
-            or file_data[:4] == b"PK\x03\x04"  # Sometimes XLS are actually ZIP
-        )
-    
-    return False
-
-
-@sync_to_async
-def load_dataframe(file_data: bytes, content_type: str, file_name: str) -> Dict[str, pd.DataFrame]:
-    """
-    Load tabular file into pandas DataFrames.
-    
-    Returns a dictionary mapping sheet/table names to DataFrames.
-    For CSV files, uses 'default' as the key.
-    For Excel files, uses sheet names as keys.
-    """
-    try:
-        # Handle CSV files - also accept text/plain if file extension is .csv
-        if content_type in ["text/csv", "application/csv"] or (
-            content_type == "text/plain" and file_name.lower().endswith(".csv")
-        ):
-            # Detect the separator
-            separator = detect_csv_separator(file_data)
-            logger.debug("Detected CSV separator: %r", separator)
-            
-            # Read CSV with detected separator
-            df = pd.read_csv(
-                BytesIO(file_data),
-                sep=separator,
-                on_bad_lines="skip",  # Skip problematic lines
-                engine="python",  # More flexible parser
-                encoding="utf-8",
-            )
-            
-            if df.empty:
-                raise ValueError("CSV file appears to be empty or could not be parsed")
-            
-            return {"default": df}
-        elif content_type in [
-            "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
-            "application/vnd.ms-excel",
-            "application/excel",
-        ] or file_name.lower().endswith((".xlsx", ".xls", ".xlsm", ".xlsb")):
-            # Validate Excel file format before attempting to read
-            if not _is_valid_excel_file(file_data, file_name):
-                logger.warning(
-                    "File '%s' does not appear to be a valid Excel file. "
-                    "File size: %d bytes, First bytes: %r",
-                    file_name,
-                    len(file_data),
-                    file_data[:20] if len(file_data) >= 20 else file_data,
-                )
-                raise ValueError(
-                    f"File '{file_name}' does not appear to be a valid Excel file. "
-                    "It may be corrupted or in an unsupported format."
-                )
-            
-            file_lower = file_name.lower()
-            dataframes = {}
-            
-            # Try different engines based on file extension
-            if file_lower.endswith(".xls"):
-                # Old Excel format - try xlrd engine
-                try:
-                    logger.debug("Attempting to read .xls file with xlrd engine")
-                    excel_file = pd.ExcelFile(BytesIO(file_data), engine="xlrd")
-                    dataframes = {
-                        sheet_name: excel_file.parse(sheet_name)
-                        for sheet_name in excel_file.sheet_names
-                    }
-                except Exception as xlrd_error:
-                    logger.warning("Failed to read .xls with xlrd: %s", xlrd_error)
-                    # Fallback: try openpyxl (sometimes .xls files are actually .xlsx)
-                    try:
-                        logger.debug("Trying openpyxl as fallback for .xls file")
-                        excel_file = pd.ExcelFile(BytesIO(file_data), engine="openpyxl")
-                        dataframes = {
-                            sheet_name: excel_file.parse(sheet_name)
-                            for sheet_name in excel_file.sheet_names
-                        }
-                    except Exception as openpyxl_error:
-                        logger.error("Failed to read .xls with both engines: %s", openpyxl_error)
-                        raise ValueError(
-                            f"Failed to read Excel file '{file_name}': "
-                            f"xlrd error: {xlrd_error}, openpyxl error: {openpyxl_error}"
-                        ) from openpyxl_error
-            else:
-                # XLSX format - try openpyxl first
-                try:
-                    logger.debug("Attempting to read Excel file with openpyxl engine")
-                    excel_file = pd.ExcelFile(BytesIO(file_data), engine="openpyxl")
-                    dataframes = {
-                        sheet_name: excel_file.parse(sheet_name)
-                        for sheet_name in excel_file.sheet_names
-                    }
-                except Exception as openpyxl_error:
-                    logger.warning("Failed to read with openpyxl: %s", openpyxl_error)
-                    # Try calamine engine if available (faster and more robust)
-                    try:
-                        logger.debug("Trying calamine engine as fallback")
-                        excel_file = pd.ExcelFile(BytesIO(file_data), engine="calamine")
-                        dataframes = {
-                            sheet_name: excel_file.parse(sheet_name)
-                            for sheet_name in excel_file.sheet_names
-                        }
-                    except ImportError:
-                        logger.debug("calamine engine not available")
-                        raise ValueError(
-                            f"Failed to read Excel file '{file_name}' with openpyxl: {openpyxl_error}. "
-                            "The file may be corrupted or in an unsupported format."
-                        ) from openpyxl_error
-                    except Exception as calamine_error:
-                        logger.error("Failed to read with calamine: %s", calamine_error)
-                        raise ValueError(
-                            f"Failed to read Excel file '{file_name}': "
-                            f"openpyxl error: {openpyxl_error}, calamine error: {calamine_error}"
-                        ) from calamine_error
-            
-            if not dataframes:
-                raise ValueError(f"Excel file '{file_name}' contains no readable sheets")
-            
-            logger.info(
-                "Successfully loaded Excel file '%s' with %d sheet(s): %s",
-                file_name,
-                len(dataframes),
-                list(dataframes.keys()),
-            )
-            return dataframes
-        else:
-            raise ValueError(f"Unsupported content type: {content_type}")
-    except Exception as e:
-        logger.error("Error loading tabular file: %s", e, exc_info=True)
-        raise ModelCannotRetry(f"Failed to load file: {str(e)}") from e
-
-
-def generate_metadata(dataframes: Dict[str, pd.DataFrame], file_name: str) -> Dict[str, Any]:
-    """
-    Generate metadata about the tabular file.
-    
-    Returns:
-        Dictionary containing:
-        - sheets: List of sheet/table names
-        - schemas: Dictionary mapping sheet names to their schemas
-        - row_counts: Dictionary mapping sheet names to row counts
-        - column_info: Dictionary mapping sheet names to column information
-    """
-    metadata = {
-        "file_name": file_name,
-        "sheets": list(dataframes.keys()),
-        "schemas": {},
-        "row_counts": {},
-        "column_info": {},
-    }
-
-    for sheet_name, df in dataframes.items():
-        # Schema: column names and types
-        metadata["schemas"][sheet_name] = {
-            col: str(dtype) for col, dtype in df.dtypes.items()
-        }
-        
-        # Row count
-        metadata["row_counts"][sheet_name] = len(df)
-        
-        # Column info: name, type, sample values, null counts
-        metadata["column_info"][sheet_name] = {}
-        for col in df.columns:
-            col_info = {
-                "type": str(df[col].dtype),
-                "null_count": int(df[col].isna().sum()),
-                "unique_count": int(df[col].nunique()),
-            }
-            # Add sample values (non-null)
-            sample_values = df[col].dropna().head(5).tolist()
-            if sample_values:
-                col_info["sample_values"] = [str(v) for v in sample_values]
-            metadata["column_info"][sheet_name][col] = col_info
-
-    return metadata
-
-
-async def generate_query(
-    user_query: str, metadata: Dict[str, Any], query_agent: BaseAgent, ctx: RunContext
-) -> str:
-    """
-    Use an LLM agent to generate a pandas query from user query and file metadata.
-    """
-    metadata_str = json.dumps(metadata, indent=2)
-    
-    prompt = f"""You are a data analysis assistant. Given a user query and file metadata, generate a Python pandas query to answer the question.
-
-File metadata:
-{metadata_str}
-
-User query: {user_query}
-
-Generate a Python code snippet that:
-1. Uses pandas operations (filter, groupby, aggregate, etc.)
-2. Works with the dataframes loaded in memory (available as 'dataframes' dict)
-3. Assigns the final result to a variable named 'result'
-4. Handles the specific sheet/table if multiple sheets exist
-5. ALWAYS handles NaN/NA values in boolean conditions using .notna() or .fillna() before filtering
-6. If the user asks for a plot/graph/chart, create it using matplotlib and save to 'plot_image' variable as base64
-
-IMPORTANT RULES:
-- The code MUST assign the final result to a variable named 'result'
-- When filtering with conditions, ALWAYS check for NaN first: df[df['col'].notna() & (df['col'] > value)]
-- Use .dropna() if you need to remove rows with missing values
-- Use .fillna() if you need to replace missing values
-- If plotting: use plt (already imported), create the plot, convert to base64:
-  ```python
-  plt.figure(figsize=(10, 6))
-  # ... your plot code ...
-  buf = BytesIO()
-  plt.savefig(buf, format='png')
-  buf.seek(0)
-  plot_image = base64.b64encode(buf.getvalue()).decode('utf-8')
-  plt.close()
-  ```
-  NOTE: Do NOT use import statements - plt, base64, BytesIO are already available.
-
-Return ONLY the Python code, without markdown formatting or explanations. The code should be executable and use variables:
-- 'dataframes': dict mapping sheet names to DataFrames
-- Sheet names available: {', '.join(metadata['sheets'])}
-
-Example format (without plot):
-df = dataframes['default']
-df = df[df['column'].notna()]  # Remove NaN values first
-result = df[df['column'] > 100].groupby('category').sum()
-
-Example format (with plot):
-df = dataframes['default']
-plt.figure(figsize=(10, 6))
-plt.plot(df.index, df['close'])
-plt.xlabel('Index')
-plt.ylabel('Close')
-plt.title('Close vs Index')
-buf = BytesIO()
-plt.savefig(buf, format='png')
-buf.seek(0)
-plot_image = base64.b64encode(buf.getvalue()).decode('utf-8')
-plt.close()
-result = "Plot generated successfully. The plot image has been saved and is available in the tool response."
-
-IMPORTANT: 
-- Do NOT use import statements in the code. All necessary modules (pd, plt, np, base64, BytesIO) are already available. Do NOT use anything else than these modules.
-- When returning the result text, mention that a plot was generated and will be available in the response, but do NOT include the URL in the text - the system will handle displaying it.
-
-Generate the query code:"""
-
-    try:
-        response = await query_agent.run(prompt, usage=ctx.usage)
-        query_code = response.output.strip()
-        
-        # Extract code from markdown code blocks if present
-        if "```python" in query_code:
-            query_code = query_code.split("```python")[1].split("```")[0].strip()
-        elif "```" in query_code:
-            query_code = query_code.split("```")[1].split("```")[0].strip()
-        
-        return query_code
-    except Exception as e:
-        logger.error("Error generating query: %s", e, exc_info=True)
-        raise ModelRetry("Failed to generate query. Please try rephrasing your question.") from e
-
-
-@sync_to_async
-def execute_query(query_code: str, dataframes: Dict[str, pd.DataFrame]) -> Any:
-    """
-    Execute the generated pandas query safely.
-    
-    Note: Uses exec() in a restricted environment. The query code is generated
-    by an LLM based on file metadata, so it should be relatively safe, but
-    we restrict the available builtins and globals.
-    """
-    try:
-        # Pre-process dataframes to handle common issues
-        processed_dataframes = {}
-        for name, df in dataframes.items():
-            # Make a copy to avoid modifying original
-            df_processed = df.copy()
-            # Replace common NaN representations
-            df_processed = df_processed.replace(["", " ", "nan", "NaN", "None", "null"], pd.NA)
-            processed_dataframes[name] = df_processed
-        
-        # Create a safe execution environment
-        safe_globals = {
-            "pd": pd,
-            "plt": plt,
-            "np": np,
-            "base64": base64,
-            "BytesIO": BytesIO,
-            "dataframes": processed_dataframes,
-            "__builtins__": {
-                "len": len,
-                "str": str,
-                "int": int,
-                "float": float,
-                "bool": bool,
-                "list": list,
-                "dict": dict,
-                "set": set,
-                "tuple": tuple,
-                "range": range,
-                "sum": sum,
-                "max": max,
-                "min": min,
-                "abs": abs,
-                "round": round,
-            },
-        }
-        
-        # Clean up query code - remove any import statements that might cause issues
-        # Split by lines and filter out import statements
-        lines = query_code.split("\n")
-        cleaned_lines = [
-            line
-            for line in lines
-            if not line.strip().startswith("import ") and not line.strip().startswith("from ")
-        ]
-        query_code = "\n".join(cleaned_lines)
-        
-        # Execute the query in a restricted namespace
-        local_vars = {}
-        exec(query_code, safe_globals, local_vars)  # noqa: S102
-        
-        # Get the result - check if 'result' variable exists, otherwise try 'df'
-        if "result" in local_vars:
-            result = local_vars["result"]
-        elif "df" in local_vars:
-            result = local_vars["df"]
-        else:
-            # If no explicit result variable, get the last expression
-            # This is a fallback - ideally the LLM should assign to 'result'
-            raise ValueError("Query must assign result to 'result' variable")
-        
-        # Check if a plot was generated
-        plot_image = None
-        if "plot_image" in local_vars:
-            plot_image = local_vars["plot_image"]
-            logger.info("Plot image generated")
-        
-        # Convert result to a serializable format
-        result = _convert_to_serializable(result)
-        
-        return {"result": result, "plot_image": plot_image}
-    except Exception as e:
-        logger.error("Error executing query: %s", e, exc_info=True)
-        # Provide more helpful error message
-        error_msg = str(e)
-        if "NaN" in error_msg or "NA" in error_msg:
-            error_msg = (
-                f"{error_msg}. "
-                "The query may need to handle missing values (NaN/NA) using .notna() or .dropna() before filtering."
-            )
-        raise ModelCannotRetry(f"Failed to execute query: {error_msg}") from e
-
-
-@last_model_retry_soft_fail
-async def data_analysis(ctx: RunContext, query: str) -> ToolReturn:
-    """
-    Analyze tabular data files (CSV, Excel) based on user query.
-    Can also generate plots/graphs/charts.
-    
-    This tool:
-    1. Loads the tabular file(s) from attachments
-    2. Generates metadata about the file structure
-    3. Uses an LLM to generate a pandas query based on user query
-    4. Executes the query and returns results
-    
-    Args:
-        ctx (RunContext): The run context containing the conversation.
-        query (str): The user's data analysis question.
-    
-    Returns:
-        ToolReturn: Contains the analysis results and metadata.
-    """
-    try:
-        # Find tabular files in attachments
-        # First, get all attachments for debugging
-        all_attachments = await sync_to_async(list)(
-            ctx.deps.conversation.attachments.all()
-        )
-        logger.info(
-            "All attachments in conversation: %s",
-            [
-                {
-                    "file_name": a.file_name,
-                    "content_type": a.content_type,
-                    "upload_state": a.upload_state,
-                    "conversion_from": a.conversion_from,
-                }
-                for a in all_attachments
-            ],
-        )
-
-        # Find tabular files - exclude converted files (they have conversion_from set)
-        # First try by content_type
-        tabular_attachments_by_type = await sync_to_async(list)(
-            ctx.deps.conversation.attachments.filter(
-                content_type__in=TABULAR_MIME_TYPES,
-                upload_state=AttachmentStatus.READY,
-            )
-            .filter(
-                Q(conversion_from__isnull=True) | Q(conversion_from="")
-            )
-        )
-        
-        # If no files found by content_type, try by file extension as fallback
-        # (some systems detect CSV as text/plain instead of text/csv)
-        if not tabular_attachments_by_type:
-            csv_extensions = [".csv", ".xlsx", ".xls"]
-            all_ready_attachments = await sync_to_async(list)(
-                ctx.deps.conversation.attachments.filter(
-                    upload_state=AttachmentStatus.READY,
-                )
-                .filter(
-                    Q(conversion_from__isnull=True) | Q(conversion_from="")
-                )
-            )
-            tabular_attachments = [
-                att
-                for att in all_ready_attachments
-                if any(att.file_name.lower().endswith(ext) for ext in csv_extensions)
-                # Exclude Markdown files (converted files have .md extension or content_type text/markdown)
-                and not att.file_name.lower().endswith(".md")
-                and att.content_type != "text/markdown"
-            ]
-            if tabular_attachments:
-                logger.info(
-                    "Found %d tabular file(s) by extension fallback (content_type was not recognized): %s",
-                    len(tabular_attachments),
-                    [f"{a.file_name} ({a.content_type})" for a in tabular_attachments],
-                )
-        else:
-            tabular_attachments = tabular_attachments_by_type
-
-        # If still no files found, check if there are converted files that might have originals
-        # This handles the case where an Excel file was converted to Markdown for RAG
-        if not tabular_attachments:
-            # Look for converted files with tabular extensions
-            csv_extensions = [".csv", ".xlsx", ".xls"]
-            converted_attachments = await sync_to_async(list)(
-                ctx.deps.conversation.attachments.filter(
-                    upload_state=AttachmentStatus.READY,
-                )
-                .exclude(
-                    Q(conversion_from__isnull=True) | Q(conversion_from="")
-                )
-            )
-            
-            # For each converted file, try to find the original
-            for converted_att in converted_attachments:
-                if any(converted_att.file_name.lower().endswith(ext) for ext in csv_extensions):
-                    # Try to find the original file using conversion_from key
-                    original_key = converted_att.conversion_from
-                    if original_key:
-                        original_attachment = await sync_to_async(
-                            ctx.deps.conversation.attachments.filter(
-                                key=original_key,
-                                upload_state=AttachmentStatus.READY,
-                            ).first
-                        )()
-                        if original_attachment:
-                            logger.info(
-                                "Found original file '%s' for converted file '%s'",
-                                original_attachment.file_name,
-                                converted_att.file_name,
-                            )
-                            tabular_attachments.append(original_attachment)
-                            break
-
-        logger.info(
-            "Found %d tabular attachment(s): %s",
-            len(tabular_attachments),
-            [f"{a.file_name} ({a.content_type})" for a in tabular_attachments],
-        )
-
-        if not tabular_attachments:
-            raise ModelCannotRetry(
-                "No tabular files (CSV or Excel) found in the conversation. "
-                "Please upload a CSV or Excel file first. "
-                "Note: If you uploaded an Excel file that was converted to Markdown for RAG, "
-                "the original file must still be available."
-            )
-
-        # Use the first tabular file
-        attachment = tabular_attachments[0]
-        logger.info("Analyzing file: %s (type: %s)", attachment.file_name, attachment.content_type)
-
-        # Load file data
-        file_data = await read_tabular_file(attachment)
-        
-        # Validate that this is actually a valid Excel/CSV file (not a converted Markdown file)
-        # Check if it's an Excel file that should have ZIP signature
-        if attachment.file_name.lower().endswith((".xlsx", ".xls", ".xlsm", ".xlsb")):
-            if not _is_valid_excel_file(file_data, attachment.file_name):
-                logger.warning(
-                    "File '%s' does not appear to be a valid Excel file. "
-                    "It may be a converted Markdown file. Searching for original...",
-                    attachment.file_name,
-                )
-                # Try to find the original file
-                # Look for an attachment with the same name but without conversion_from
-                original_attachment = await sync_to_async(
-                    ctx.deps.conversation.attachments.filter(
-                        file_name=attachment.file_name,
-                        upload_state=AttachmentStatus.READY,
-                    )
-                    .filter(
-                        Q(conversion_from__isnull=True) | Q(conversion_from="")
-                    )
-                    .exclude(pk=attachment.pk)
-                    .first
-                )()
-                
-                if original_attachment:
-                    logger.info(
-                        "Found original file '%s' (key: %s), using it instead",
-                        original_attachment.file_name,
-                        original_attachment.key,
-                    )
-                    attachment = original_attachment
-                    file_data = await read_tabular_file(attachment)
-                elif hasattr(attachment, 'conversion_from') and attachment.conversion_from:
-                    # Try to find by key if this file has a conversion_from
-                    original_attachment = await sync_to_async(
-                        ctx.deps.conversation.attachments.filter(
-                            key=attachment.conversion_from,
-                            upload_state=AttachmentStatus.READY,
-                        ).first
-                    )()
-                    if original_attachment:
-                        logger.info(
-                            "Found original file via conversion_from: '%s'",
-                            original_attachment.file_name,
-                        )
-                        attachment = original_attachment
-                        file_data = await read_tabular_file(attachment)
-                    else:
-                        raise ModelCannotRetry(
-                            f"File '{attachment.file_name}' appears to be a converted Markdown file, "
-                            "not the original Excel file. The original file is not available. "
-                            "Please re-upload the original Excel file."
-                        )
-                else:
-                    raise ModelCannotRetry(
-                        f"File '{attachment.file_name}' does not appear to be a valid Excel file. "
-                        "It may be corrupted or in an unsupported format."
-                    )
-
-        # Load into pandas DataFrames
-        dataframes = await load_dataframe(file_data, attachment.content_type, attachment.file_name)
-
-        # Generate metadata
-        metadata = generate_metadata(dataframes, attachment.file_name)
-        logger.debug("File metadata: %s", json.dumps(metadata, indent=2))
-
-        # Generate query using LLM
-        # NOTE:
-        # We intentionally create a "bare" Agent instance here instead of using BaseAgent
-        # with tools enabled. Using BaseAgent would attach all configured tools (including
-        # this data_analysis tool itself), which can cause the model to try to call tools
-        # while we're already inside a tool execution, leading to nested tool calls and
-        # failures like "Failed to generate query. Please try rephrasing your question.".
-        #
-        # Here we reuse the same model configuration as BaseAgent but WITHOUT any tools,
-        # so this internal call is purely text-to-text.
-        llm_config = settings.LLM_CONFIGURATIONS[settings.LLM_DEFAULT_MODEL_HRID]
-        if llm_config.is_custom:
-            model_instance = prepare_custom_model(llm_config)
-        else:
-            # Rely on pydantic-ai's built-in model registry / name inference
-            model_instance = llm_config.model_name
-
-        # Use the same keyword as when using BaseAgent, which forwards to Agent.
-        # On the current pydantic_ai version, the correct kwarg is `output_type`,
-        # not `result_type` (passing `result_type` raises a UserError).
-        query_agent = Agent(model=model_instance, output_type=str)
-        query_code = await generate_query(query, metadata, query_agent, ctx)
-        logger.debug("Generated query: %s", query_code)
-
-        # Execute query
-        try:
-            execution_result = await execute_query(query_code, dataframes)
-            result = execution_result.get("result")
-            plot_image_base64 = execution_result.get("plot_image")
-        except Exception as e:
-            logger.error("Query execution failed: %s", e, exc_info=True)
-            raise ModelRetry(
-                f"Failed to execute the generated query: {str(e)}. "
-                "Please try rephrasing your question."
-            ) from e
-
-        # Format result for return
-        return_value = {
-            "query": query,
-            "query_code": query_code,
-            "result": result,
-            "metadata": metadata,
-        }
-        
-        # Save plot image to storage if generated
-        plot_url = None
-        plot_attachment = None
-        if plot_image_base64:
-            try:
-                # Decode base64 image
-                plot_image_data = base64.b64decode(plot_image_base64)
-                
-                # Generate a unique filename for the plot
-                plot_filename = f"plot_{uuid.uuid4().hex[:8]}.png"
-                plot_key = f"{ctx.deps.conversation.pk}/plots/{plot_filename}"
-                
-                # Save to storage
-                await sync_to_async(default_storage.save)(
-                    plot_key, BytesIO(plot_image_data)
-                )
-                
-                # Create a permanent attachment record in the database
-                plot_attachment = await sync_to_async(ChatConversationAttachment.objects.create)(
-                    conversation=ctx.deps.conversation,
-                    uploaded_by=ctx.deps.user,
-                    key=plot_key,
-                    file_name=plot_filename,
-                    content_type="image/png",
-                    upload_state=AttachmentStatus.READY,
-                    size=len(plot_image_data),
-                )
-                
-                # Generate presigned URL for immediate access (valid for 1 hour)
-                plot_url = await sync_to_async(generate_retrieve_policy)(plot_key)
-                logger.info(
-                    "Plot image saved to storage and database: %s (presigned URL: %s)", 
-                    plot_key, 
-                    plot_url[:50] + "..."
-                )
-            except Exception as e:
-                logger.error("Failed to save plot image: %s", e, exc_info=True)
-                # Continue without plot URL if save fails
-        
-        if plot_url:
-            # Include both local and presigned URLs
-            return_value["plot_url"] = plot_url  # Presigned URL for direct access
-            return_value["plot_local_url"] = f"/media-key/{plot_key}"  # Local URL for reference
-            # Include attachment ID for reference
-            if plot_attachment:
-                return_value["plot_attachment_id"] = str(plot_attachment.pk)
-        
-        return ToolReturn(
-            return_value=return_value,
-            metadata={"file_name": attachment.file_name, "content_type": attachment.content_type},
-        )
-
-    except (ModelCannotRetry, ModelRetry):
-        # Re-raise these as-is
-        raise
-    except Exception as exc:
-        # Unexpected error - stop and inform user
-        logger.exception("Unexpected error in data_analysis: %s", exc)
-        raise ModelCannotRetry(
-            f"An unexpected error occurred during data analysis: {type(exc).__name__}. "
-            "You must explain this to the user and not try to answer based on your knowledge."
-        ) from exc
-
-
-def add_data_analysis_tool(agent: Agent) -> None:
-    """Add the data analysis tool to an existing agent."""
-
-    @agent.tool(retries=2)
-    @functools.wraps(data_analysis)
-    async def data_analysis_tool(ctx: RunContext, query: str) -> ToolReturn:
-        """
-        Analyze tabular data files (CSV, Excel) based on user query.
-        
-        This tool loads tabular files, generates metadata about their structure,
-        uses an LLM to generate a pandas query based on the user's question,
-        executes the query, and returns the results.
-        
-        Use this tool when the user asks questions about data in CSV or Excel files,
-        such as:
-        - "What is the average sales by region?"
-        - "Show me the top 10 products by revenue"
-        - "How many records are in this file?"
-        - "Filter data where column X is greater than Y"
-        
-        Args:
-            ctx (RunContext): The run context containing the conversation.
-            query (str): The user's data analysis question.
-        """
-        # Import here to avoid circular import
-        from chat.tools.data_analysis import data_analysis as _data_analysis
-        
-        return await _data_analysis(ctx, query)
-
-    @agent.instructions
-    def data_analysis_instructions() -> str:
-        """Dynamic system prompt function to add data analysis instructions."""
-        return (
-            "When the user asks questions about data in CSV or Excel files, "
-            "use the data_analysis tool to analyze the data and answer their question. "
-            "The tool will handle loading the file, generating queries, and executing them. "
-            "When a plot is generated, the tool returns a 'plot_url' in the result. "
-            "Use this presigned URL directly in markdown image syntax: ![Description](plot_url). "
-            "Do NOT use local URLs like /media-key/... - always use the presigned URL from plot_url. "
-            "Present the results clearly to the user."
-        )
-

src/backend/chat/tools/document_search_rag.py

@@ -26,7 +26,7 @@ def add_document_rag_search_tool(agent: Agent) -> None:
 
         document_store = document_store_backend(ctx.deps.conversation.collection_id)
 
-        rag_results = document_store.search(query)
+        rag_results = document_store.search(query, session=ctx.deps.session)
 
         ctx.usage += RunUsage(
             input_tokens=rag_results.usage.prompt_tokens,

src/backend/chat/tools/web_search_brave.py

@@ -127,7 +127,7 @@ async def _extract_and_summarize_snippets_async(query: str, url: str) -> List[st
         return []
 
 
-async def _fetch_and_store_async(url: str, document_store) -> None:
+async def _fetch_and_store_async(url: str, document_store, **kwargs) -> None:
     """Fetch, extract and store text content from the URL in the document store."""
 
     try:
@@ -136,7 +136,7 @@ async def _fetch_and_store_async(url: str, document_store) -> None:
         logger.debug("Fetched document: %s", document)
 
         if document:
-            await document_store.astore_document(url, document)
+            await document_store.astore_document(url, document, **kwargs)
     except DocumentFetchError as e:
         logger.warning("Failed to fetch and store %s: %s", url, e)
         # Continue with other documents
@@ -307,19 +307,26 @@ async def web_search_brave_with_document_backend(ctx: RunContext, query: str) ->
         temp_collection_name = f"tmp-{uuid.uuid4()}"
         try:
             async with document_store_backend.temporary_collection_async(
-                temp_collection_name
+                temp_collection_name, session=ctx.deps.session
             ) as document_store:
                 # Fetch and store all documents concurrently
                 tasks = [
-                    _fetch_and_store_async(result["url"], document_store)
+                    _fetch_and_store_async(
+                        result["url"],
+                        document_store,
+                        user_sub=ctx.deps.user.sub,
+                        session=ctx.deps.session,
+                    )
                     for result in raw_search_results
                 ]
                 await asyncio.gather(*tasks, return_exceptions=True)
 
                 # Perform RAG search
                 rag_results = await document_store.asearch(
-                    query,
+                    query=query,
                     results_count=settings.BRAVE_RAG_WEB_SEARCH_CHUNK_NUMBER,
+                    session=ctx.deps.session,
+                    user_sub=ctx.deps.user.sub,
                 )
                 logger.info("RAG search returned:  %s", rag_results)
 

src/backend/chat/vercel_ai_sdk/encoder/__init__.py

@@ -2,6 +2,6 @@
 This module contains the EventEncoder class.
 """
 
-from .encoder import EventEncoder
+from .encoder import CURRENT_EVENT_ENCODER_VERSION, EventEncoder, EventEncoderVersion
 
-__all__ = ["EventEncoder"]
+__all__ = ["EventEncoder", "CURRENT_EVENT_ENCODER_VERSION", "EventEncoderVersion"]

src/backend/chat/vercel_ai_sdk/encoder/encoder.py

@@ -1,6 +1,7 @@
 """Event Encoder for Vercel AI SDK"""
 
-from typing import Literal, Union
+from enum import Enum
+from typing import Union
 
 from ..core.events_v4 import BaseEvent as V4BaseEvent
 from ..core.events_v4 import TextPart
@@ -8,16 +9,26 @@ from ..core.events_v5 import BaseEvent as V5BaseEvent
 from ..core.events_v5 import TextDeltaEvent
 
 
+class EventEncoderVersion(str, Enum):
+    """Enumeration of supported event encoder versions."""
+
+    V4 = "v4"
+    V5 = "v5"
+
+
+CURRENT_EVENT_ENCODER_VERSION = EventEncoderVersion.V4  # used encoder version
+
+
 class EventEncoder:
     """
     Encodes events for the Vercel AI SDK based on the specified version.
     """
 
-    def __init__(self, version: Literal["v4", "v5"] = None):
+    def __init__(self, version: EventEncoderVersion):
         """
         Initializes the EventEncoder with the specified version.
         """
-        if version not in ["v4", "v5"]:
+        if version not in [EventEncoderVersion.V4, EventEncoderVersion.V5]:
             raise ValueError("Unsupported version. Supported versions are 'v4' and 'v5'.")
 
         self.version = version
@@ -28,7 +39,7 @@ class EventEncoder:
         """
         return "text/event-stream"
 
-    def encode(self, event: Union[V5BaseEvent, V5BaseEvent]) -> str | None:
+    def encode(self, event: Union[V4BaseEvent, V5BaseEvent]) -> str | None:
         """
         Encodes an event based on the version.
 
@@ -38,15 +49,15 @@ class EventEncoder:
             str | None: The encoded event as a string,
             or None if the event type is not adapted to the SDK version.
         """
-        if self.version == "v4" and isinstance(event, V4BaseEvent):
+        if self.version == EventEncoderVersion.V4 and isinstance(event, V4BaseEvent):
             return self._encode_v4_streaming(event)
 
-        if self.version == "v5" and isinstance(event, V5BaseEvent):
+        if self.version == EventEncoderVersion.V5 and isinstance(event, V5BaseEvent):
             return self._encode_sse(event)
 
         return None
 
-    def encode_text(self, event: Union[V5BaseEvent, V5BaseEvent]) -> str | None:
+    def encode_text(self, event: Union[V4BaseEvent, V5BaseEvent]) -> str | None:
         """
         Encodes an event based on the version.
 
@@ -56,10 +67,10 @@ class EventEncoder:
             str | None: The encoded event as a string,
             or None if the event type is not adapted to the SDK version.
         """
-        if self.version == "v4" and isinstance(event, TextPart):
+        if self.version == EventEncoderVersion.V4 and isinstance(event, TextPart):
             return event.text
 
-        if self.version == "v5" and isinstance(event, TextDeltaEvent):
+        if self.version == EventEncoderVersion.V5 and isinstance(event, TextDeltaEvent):
             return event.delta
 
         return None
@@ -70,7 +81,7 @@ class EventEncoder:
         """
         return f"{event.type}:{event.model_dump_json(by_alias=True, exclude={'type'})}\n"
 
-    def _encode_sse(self, event: Union[V5BaseEvent, V5BaseEvent]) -> str:
+    def _encode_sse(self, event: Union[V4BaseEvent, V5BaseEvent]) -> str:
         """
         Encodes an event into an SSE string.
         """

src/backend/chat/views.py

@@ -7,11 +7,13 @@ from uuid import uuid4
 from django.conf import settings
 from django.core.files.storage import default_storage
 from django.http import Http404, StreamingHttpResponse
+from django.utils.decorators import method_decorator
 
 import langfuse
 import magic
 import posthog
 from lasuite.malware_detection import malware_detection
+from lasuite.oidc_login.decorators import refresh_oidc_access_token
 from rest_framework import decorators, filters, mixins, permissions, status, viewsets
 from rest_framework.exceptions import MethodNotAllowed, PermissionDenied, ValidationError
 from rest_framework.response import Response
@@ -26,6 +28,7 @@ from core.filters import remove_accents
 from activation_codes.permissions import IsActivatedUser
 from chat import models, serializers
 from chat.clients.pydantic_ai import AIAgentService
+from chat.keepalive import stream_with_keepalive_async, stream_with_keepalive_sync
 from chat.serializers import ChatConversationRequestSerializer
 
 logger = logging.getLogger(__name__)
@@ -122,6 +125,7 @@ class ChatViewSet(  # pylint: disable=too-many-ancestors, abstract-method
             self.permission_classes = []
         return super().get_permissions()
 
+    @method_decorator(refresh_oidc_access_token)
     @decorators.action(
         methods=["post"],
         detail=True,
@@ -173,6 +177,7 @@ class ChatViewSet(  # pylint: disable=too-many-ancestors, abstract-method
         ai_service = AIAgentService(
             conversation=conversation,
             user=self.request.user,
+            session=request.session,
             model_hrid=model_hrid,
             language=(
                 self.request.user.language
@@ -188,29 +193,28 @@ class ChatViewSet(  # pylint: disable=too-many-ancestors, abstract-method
         if is_async_mode:
             logger.debug("Using ASYNC streaming for chat conversation.")
             if protocol == "data":
-                streaming_content = ai_service.stream_data_async(
+                base_stream = ai_service.stream_data_async(
                     messages, force_web_search=force_web_search
                 )
             else:  # Default to 'text' protocol
-                streaming_content = ai_service.stream_text_async(
+                base_stream = ai_service.stream_text_async(
                     messages, force_web_search=force_web_search
                 )
+            streaming_content = stream_with_keepalive_async(base_stream)
         else:
             logger.debug("Using SYNC streaming for chat conversation.")
             if protocol == "data":
-                streaming_content = ai_service.stream_data(
-                    messages, force_web_search=force_web_search
-                )
+                base_stream = ai_service.stream_data(messages, force_web_search=force_web_search)
             else:  # Default to 'text' protocol
-                streaming_content = ai_service.stream_text(
-                    messages, force_web_search=force_web_search
-                )
+                base_stream = ai_service.stream_text(messages, force_web_search=force_web_search)
 
+            streaming_content = stream_with_keepalive_sync(base_stream)
         response = StreamingHttpResponse(
             streaming_content,
             content_type="text/event-stream",
             headers={
                 "x-vercel-ai-data-stream": "v1",  # This header is used for Vercel AI streaming,
+                "X-Accel-Buffering": "no",  # Prevent nginx buffering
             },
         )
         return response
@@ -371,7 +375,6 @@ class ChatConversationAttachmentViewSet(
             owner=self.request.user,
         ).exists():
             raise Http404
-
         file_name = serializer.validated_data["file_name"]
         extension = file_name.rpartition(".")[-1] if "." in file_name else None
 

src/backend/conftest.py

@@ -22,7 +22,7 @@ def no_http_requests(monkeypatch):
     Credits: https://blog.jerrycodes.com/no-http-requests/
     """
 
-    allowed_hosts = {"localhost", "minio", "minio:9000"}
+    allowed_hosts = {"localhost", "127.0.0.1", "minio", "minio:9000"}
     original_urlopen = HTTPConnectionPool.urlopen
 
     def urlopen_mock(self, method, url, *args, **kwargs):

src/backend/conversations/settings.py

@@ -841,6 +841,23 @@ USER QUESTION:
         environ_prefix=None,
     )
 
+    # Find
+    FIND_API_KEY = values.Value(
+        None,
+        environ_name="FIND_API_KEY",
+        environ_prefix=None,
+    )
+    FIND_API_URL = values.Value(
+        "https://app-find/api",
+        environ_name="FIND_API_URL",
+        environ_prefix=None,
+    )
+    FIND_API_TIMEOUT = values.PositiveIntegerValue(
+        default=30,  # seconds
+        environ_name="FIND_API_TIMEOUT",
+        environ_prefix=None,
+    )
+
     # Logging
     # We want to make it easy to log to console but by default we log production
     # to Sentry and don't want to log to console.
@@ -911,7 +928,9 @@ USER QUESTION:
     LANGFUSE_MEDIA_UPLOAD_ENABLED = values.BooleanValue(
         default=False, environ_name="LANGFUSE_MEDIA_UPLOAD_ENABLED", environ_prefix=None
     )
-
+    AUTO_TITLE_AFTER_USER_MESSAGES = values.PositiveIntegerValue(
+        default=None, environ_name="AUTO_TITLE_AFTER_USER_MESSAGES", environ_prefix=None
+    )
     # WARNING: Testing purpose only. Do not use in production.
     WARNING_MOCK_CONVERSATION_AGENT = values.BooleanValue(
         default=False,
@@ -919,6 +938,12 @@ USER QUESTION:
         environ_prefix=None,
     )
 
+    # Default keepalive interval: 55s (safely below typical 60s proxy timeouts)
+    # Prevents connection drops during long stream pauses while providing 5s safety margin.
+    KEEPALIVE_INTERVAL = values.PositiveIntegerValue(
+        default=55, environ_name="KEEPALIVE_INTERVAL", environ_prefix=None
+    )
+
     # pylint: disable=invalid-name
     @property
     def ENVIRONMENT(self):
@@ -1131,6 +1156,8 @@ class Test(Base):
 
     POSTHOG_KEY = None
 
+    AUTO_TITLE_AFTER_USER_MESSAGES = None
+
     def __init__(self):
         # pylint: disable=invalid-name
         self.INSTALLED_APPS += ["drf_spectacular_sidecar"]

src/backend/locale/de_DE/LC_MESSAGES/django.po

@@ -3,7 +3,7 @@ msgstr ""
 "Project-Id-Version: la-suite-conversations\n"
 "Report-Msgid-Bugs-To: \n"
 "POT-Creation-Date: 2025-10-20 21:48+0000\n"
-"PO-Revision-Date: 2025-12-15 13:49\n"
+"PO-Revision-Date: 2026-01-16 11:04\n"
 "Last-Translator: \n"
 "Language-Team: German\n"
 "Language: de_DE\n"

src/backend/locale/en_US/LC_MESSAGES/django.po

@@ -3,7 +3,7 @@ msgstr ""
 "Project-Id-Version: la-suite-conversations\n"
 "Report-Msgid-Bugs-To: \n"
 "POT-Creation-Date: 2025-10-20 21:48+0000\n"
-"PO-Revision-Date: 2025-12-15 13:49\n"
+"PO-Revision-Date: 2026-01-16 11:04\n"
 "Last-Translator: \n"
 "Language-Team: English\n"
 "Language: en_US\n"

src/backend/locale/fr_FR/LC_MESSAGES/django.po

@@ -3,7 +3,7 @@ msgstr ""
 "Project-Id-Version: la-suite-conversations\n"
 "Report-Msgid-Bugs-To: \n"
 "POT-Creation-Date: 2025-10-20 21:48+0000\n"
-"PO-Revision-Date: 2025-12-15 13:49\n"
+"PO-Revision-Date: 2026-01-16 11:04\n"
 "Last-Translator: \n"
 "Language-Team: French\n"
 "Language: fr_FR\n"

src/backend/locale/nl_NL/LC_MESSAGES/django.po

@@ -3,7 +3,7 @@ msgstr ""
 "Project-Id-Version: la-suite-conversations\n"
 "Report-Msgid-Bugs-To: \n"
 "POT-Creation-Date: 2025-10-20 21:48+0000\n"
-"PO-Revision-Date: 2025-12-15 13:49\n"
+"PO-Revision-Date: 2026-01-16 11:04\n"
 "Last-Translator: \n"
 "Language-Team: Dutch\n"
 "Language: nl_NL\n"

src/backend/locale/ru_RU/LC_MESSAGES/django.po

@@ -3,7 +3,7 @@ msgstr ""
 "Project-Id-Version: la-suite-conversations\n"
 "Report-Msgid-Bugs-To: \n"
 "POT-Creation-Date: 2025-10-20 21:48+0000\n"
-"PO-Revision-Date: 2025-12-15 13:49\n"
+"PO-Revision-Date: 2026-01-16 11:04\n"
 "Last-Translator: \n"
 "Language-Team: Russian\n"
 "Language: ru_RU\n"

src/backend/locale/uk_UA/LC_MESSAGES/django.po

@@ -3,7 +3,7 @@ msgstr ""
 "Project-Id-Version: la-suite-conversations\n"
 "Report-Msgid-Bugs-To: \n"
 "POT-Creation-Date: 2025-10-20 21:48+0000\n"
-"PO-Revision-Date: 2025-12-15 13:49\n"
+"PO-Revision-Date: 2026-01-16 11:04\n"
 "Last-Translator: \n"
 "Language-Team: Ukrainian\n"
 "Language: uk_UA\n"

src/backend/pyproject.toml

@@ -46,6 +46,7 @@ dependencies = [
     "easy_thumbnails==2.10.1",
     "factory_boy==3.3.3",
     "gunicorn==23.0.0",
+    "jaraco.context>=6.1.0",
     "jsonschema==4.25.1",
     "langfuse==3.10.0",
     "lxml==5.4.0",
@@ -53,10 +54,6 @@ dependencies = [
     "markitdown==0.0.2",
     "mozilla-django-oidc==4.0.1",
     "nested-multipart-parser==1.6.0",
-    "matplotlib==3.9.2",
-    "numpy==2.1.3",
-    "openpyxl==3.1.5",
-    "pandas==2.2.3",
     "posthog==7.0.0",
     "pydantic==2.12.4",
     "pydantic-ai-slim[openai,mistral,mcp,evals,logfire]==1.17.0",

src/backend/utils/oidc.py

@@ -0,0 +1,54 @@
+"""Utility functions for OIDC token management."""
+
+from functools import wraps
+
+from django.conf import settings
+
+import requests
+from lasuite.oidc_login.backends import get_oidc_refresh_token, store_tokens
+from rest_framework.exceptions import AuthenticationFailed
+
+
+def refresh_access_token(session):
+    """Refresh the OIDC access token using the refresh token."""
+    refresh_token = get_oidc_refresh_token(session)
+    if not refresh_token:
+        raise AuthenticationFailed({"error": "Refresh token is missing from session"})
+
+    response = requests.post(
+        settings.OIDC_OP_TOKEN_ENDPOINT,
+        data={
+            "grant_type": "refresh_token",
+            "client_id": settings.OIDC_RP_CLIENT_ID,
+            "client_secret": settings.OIDC_RP_CLIENT_SECRET,
+            "refresh_token": refresh_token,
+        },
+        timeout=5,
+    )
+    response.raise_for_status()
+    token_info = response.json()
+
+    store_tokens(
+        session,
+        access_token=token_info.get("access_token"),
+        id_token=None,
+        refresh_token=token_info.get("refresh_token"),
+    )
+    return session
+
+
+def with_fresh_access_token(func):
+    """
+    Decorator to handle OIDC token refresh and extraction.
+    Expects 'session' in kwargs and update it with the fresh token.
+    """
+
+    @wraps(func)
+    def wrapper(*args, **kwargs):
+        session = kwargs.pop("session", None)
+        if session is None:
+            raise AuthenticationFailed({"error": "Session is required but not provided"})
+        refreshed_session = refresh_access_token(session)
+        return func(*args, session=refreshed_session, **kwargs)
+
+    return wrapper

src/frontend/apps/conversations/package.json

@@ -1,6 +1,6 @@
 {
   "name": "app-conversations",
-  "version": "0.0.10",
+  "version": "0.0.11",
   "private": true,
   "scripts": {
     "dev": "next dev",
@@ -9,6 +9,7 @@
     "build-theme": "cunningham -g css,ts -o src/cunningham --utility-classes && yarn prettier && yarn stylelint --fix",
     "start": "npx -y serve@latest out",
     "lint": "tsc --noEmit && next lint",
+    "lint:fix": "tsc --noEmit && next lint --fix",
     "prettier": "prettier --write .",
     "stylelint": "stylelint \"**/*.css\"",
     "test": "jest",

src/frontend/apps/conversations/src/features/chat/api/useChat.tsx

@@ -1,6 +1,9 @@
 import { UseChatOptions, useChat as useAiSdkChat } from '@ai-sdk/react';
+import { useQueryClient } from '@tanstack/react-query';
+import { useEffect } from 'react';
 
 import { fetchAPI } from '@/api';
+import { KEY_LIST_CONVERSATION } from '@/features/chat/api/useConversations';
 import { useChatPreferencesStore } from '@/features/chat/stores/useChatPreferencesStore';
 
 const fetchAPIAdapter = (input: RequestInfo | URL, init?: RequestInit) => {
@@ -36,10 +39,46 @@ const fetchAPIAdapter = (input: RequestInfo | URL, init?: RequestInit) => {
   return fetchAPI(url, init);
 };
 
+interface ConversationMetadataEvent {
+  type: 'conversation_metadata';
+  conversationId: string;
+  title: string;
+}
+// Type guard to check if an item is a ConversationMetadataEvent
+function isConversationMetadataEvent(
+  item: unknown,
+): item is ConversationMetadataEvent {
+  return (
+    typeof item === 'object' &&
+    item !== null &&
+    'type' in item &&
+    item.type === 'conversation_metadata' &&
+    'conversationId' in item &&
+    typeof item.conversationId === 'string' &&
+    'title' in item &&
+    typeof item.title === 'string'
+  );
+}
+
 export function useChat(options: Omit<UseChatOptions, 'fetch'>) {
-  return useAiSdkChat({
+  const queryClient = useQueryClient();
+
+  const result = useAiSdkChat({
     ...options,
     maxSteps: 3,
     fetch: fetchAPIAdapter,
   });
+
+  useEffect(() => {
+    if (result.data && Array.isArray(result.data)) {
+      for (const item of result.data) {
+        if (isConversationMetadataEvent(item)) {
+          void queryClient.invalidateQueries({
+            queryKey: [KEY_LIST_CONVERSATION],
+          });
+        }
+      }
+    }
+  }, [result.data, queryClient]);
+  return result;
 }

src/frontend/apps/conversations/src/features/chat/api/useRenameConversation.tsx

@@ -0,0 +1,62 @@
+import {
+  UseMutationOptions,
+  useMutation,
+  useQueryClient,
+} from '@tanstack/react-query';
+
+import { APIError, errorCauses, fetchAPI } from '@/api';
+
+import { KEY_LIST_CONVERSATION } from './useConversations';
+
+interface RenameConversationProps {
+  conversationId: string;
+  title: string;
+}
+
+export const renameConversation = async ({
+  conversationId,
+  title,
+}: RenameConversationProps): Promise<void> => {
+  const response = await fetchAPI(`chats/${conversationId}/`, {
+    method: 'PUT',
+    body: JSON.stringify({
+      title,
+    }),
+  });
+
+  if (!response.ok) {
+    throw new APIError(
+      'Failed to rename the conversation',
+      await errorCauses(response),
+    );
+  }
+};
+
+type UseRenameConversationOptions = UseMutationOptions<
+  void,
+  APIError,
+  RenameConversationProps
+>;
+
+export const useRenameConversation = (
+  options?: UseRenameConversationOptions,
+) => {
+  const queryClient = useQueryClient();
+  return useMutation<void, APIError, RenameConversationProps>({
+    mutationFn: renameConversation,
+    ...options,
+    onSuccess: (data, variables, context) => {
+      void queryClient.invalidateQueries({
+        queryKey: [KEY_LIST_CONVERSATION],
+      });
+      if (options?.onSuccess) {
+        void options.onSuccess(data, variables, context);
+      }
+    },
+    onError: (error, variables, context) => {
+      if (options?.onError) {
+        void options.onError(error, variables, context);
+      }
+    },
+  });
+};

src/frontend/apps/conversations/src/features/chat/components/Chat.tsx

@@ -1,9 +1,4 @@
-import {
-  Message,
-  ReasoningUIPart,
-  SourceUIPart,
-  ToolInvocationUIPart,
-} from '@ai-sdk/ui-utils';
+import { Message, SourceUIPart, ToolInvocationUIPart } from '@ai-sdk/ui-utils';
 import { Modal, ModalSize } from '@openfun/cunningham-react';
 import 'katex/dist/katex.min.css'; // `rehype-katex` does not import the CSS for you
 import { useRouter } from 'next/router';
@@ -816,30 +811,12 @@ export const Chat = ({
                             </Box>
                           )}
                         {message.parts
-                          ?.filter(
-                            (part) =>
-                              part.type === 'reasoning' ||
-                              part.type === 'tool-invocation',
-                          )
+                          ?.filter((part) => part.type === 'tool-invocation')
                           .map(
-                            (
-                              part: ReasoningUIPart | ToolInvocationUIPart,
-                              partIndex: number,
-                            ) =>
-                              part.type === 'reasoning' ? (
-                                <Box
-                                  key={`reasoning-${partIndex}`}
-                                  $background="var(--c--theme--colors--greyscale-100)"
-                                  $color="var(--c--theme--colors--greyscale-500)"
-                                  $padding={{ all: 'sm' }}
-                                  $radius="md"
-                                  $css="font-size: 0.9em;"
-                                >
-                                  {part.reasoning}
-                                </Box>
-                              ) : part.type === 'tool-invocation' &&
-                                isCurrentlyStreaming &&
-                                isLastAssistantMessageInConversation ? (
+                            (part: ToolInvocationUIPart, partIndex: number) =>
+                              part.type === 'tool-invocation' &&
+                              isCurrentlyStreaming &&
+                              isLastAssistantMessageInConversation ? (
                                 <ToolInvocationItem
                                   key={`tool-invocation-${partIndex}`}
                                   toolInvocation={part.toolInvocation}

src/frontend/apps/conversations/src/features/left-panel/components/ConversationItemActions.tsx

@@ -1,4 +1,4 @@
-import { Button as _Button, useModal } from '@openfun/cunningham-react';
+import { useModal } from '@openfun/cunningham-react';
 import { useTranslation } from 'react-i18next';
 import { css } from 'styled-components';
 
@@ -6,6 +6,7 @@ import { DropdownMenu, DropdownMenuOption, Icon } from '@/components';
 import { ChatConversation } from '@/features/chat/types';
 
 import { ModalRemoveConversation } from './ModalRemoveConversation';
+import { ModalRenameConversation } from './ModalRenameConversation';
 
 interface ConversationItemActionsProps {
   conversation: ChatConversation;
@@ -17,8 +18,16 @@ export const ConversationItemActions = ({
   const { t } = useTranslation();
 
   const deleteModal = useModal();
+  const renameModal = useModal();
 
   const options: DropdownMenuOption[] = [
+    {
+      label: t('Rename chat'),
+      icon: 'edit',
+      callback: () => renameModal.open(),
+      disabled: false,
+      testId: `conversation-item-actions-rename-${conversation.id}`,
+    },
     {
       label: t('Delete chat'),
       icon: 'delete',
@@ -71,6 +80,12 @@ export const ConversationItemActions = ({
           conversation={conversation}
         />
       )}
+      {renameModal.isOpen && (
+        <ModalRenameConversation
+          onClose={renameModal.onClose}
+          conversation={conversation}
+        />
+      )}
     </>
   );
 };

src/frontend/apps/conversations/src/features/left-panel/components/LeftPanelConversationItem.tsx

@@ -58,7 +58,7 @@ export const LeftPanelConversationItem = ({
     >
       <StyledLink
         href={`/chat/${conversation.id}/`}
-        $css="overflow: auto; flex-grow: 1;"
+        $css="overflow: auto; flex-grow: 1; color: var(--c--theme--colors--greyscale-900);"
         onClick={handleLinkClick}
       >
         <SimpleConversationItem showAccesses conversation={conversation} />

src/frontend/apps/conversations/src/features/left-panel/components/ModalRemoveConversation.tsx

@@ -46,7 +46,7 @@ export const ModalRemoveConversation = ({
         <>
           <Button
             aria-label={t('Close the modal')}
-            color="secondary"
+            color="tertiary"
             fullWidth
             onClick={() => onClose()}
           >
@@ -79,7 +79,10 @@ export const ModalRemoveConversation = ({
         </Text>
       }
     >
-      <Box className="--converstions--modal-remove-chat">
+      <Box
+        className="--conversations--modal-remove-chat"
+        data-testid="delete-chat-confirm"
+      >
         <Text $size="sm" $variation="600">
           {t('Are you sure you want to delete this conversation ?')}
         </Text>

src/frontend/apps/conversations/src/features/left-panel/components/ModalRenameConversation.tsx

@@ -0,0 +1,108 @@
+import { Button, Input, Modal, ModalSize } from '@openfun/cunningham-react';
+import { useState } from 'react';
+import { useTranslation } from 'react-i18next';
+
+import { Box, Text, useToast } from '@/components';
+import { useRenameConversation } from '@/features/chat/api/useRenameConversation';
+import { ChatConversation } from '@/features/chat/types';
+
+interface ModalRenameConversationProps {
+  onClose: () => void;
+  conversation: ChatConversation;
+}
+
+export const ModalRenameConversation = ({
+  onClose,
+  conversation,
+}: ModalRenameConversationProps) => {
+  const { showToast } = useToast();
+  const { t } = useTranslation();
+  const { mutate: renameConversation } = useRenameConversation({
+    onSuccess: () => {
+      showToast(
+        'success',
+        t('The conversation has been renamed.'),
+        undefined,
+        4000,
+      );
+      onClose();
+    },
+    onError: (error) => {
+      const errorMessage =
+        error.cause?.[0] ||
+        error.message ||
+        t('An error occurred while renaming the conversation');
+      showToast('error', errorMessage, undefined, 4000);
+    },
+  });
+
+  const [newName, setNewName] = useState(conversation.title ?? '');
+  const handleSubmit = (e: React.FormEvent) => {
+    e.preventDefault();
+    const trimmedNewName = newName.trim();
+    if (trimmedNewName) {
+      renameConversation({
+        conversationId: conversation.id,
+        title: trimmedNewName,
+      });
+    }
+  };
+  return (
+    <Modal
+      isOpen
+      closeOnClickOutside
+      onClose={() => onClose()}
+      aria-label={t('Content modal to rename a conversation')}
+      rightActions={
+        <>
+          <Button
+            aria-label={t('Close the modal')}
+            color="tertiary"
+            onClick={() => onClose()}
+          >
+            {t('Cancel')}
+          </Button>
+          <Button
+            aria-label={t('Rename chat')}
+            color="primary"
+            type="submit"
+            form="rename-chat-form"
+          >
+            {t('Rename')}
+          </Button>
+        </>
+      }
+      size={ModalSize.SMALL}
+      title={
+        <Text
+          $size="h6"
+          as="h6"
+          $margin={{ all: '0' }}
+          $align="flex-start"
+          $variation="1000"
+        >
+          {t('Rename chat')}
+        </Text>
+      }
+    >
+      <Box className="--conversations--modal-rename-chat">
+        <form
+          onSubmit={handleSubmit}
+          id="rename-chat-form"
+          data-testid="rename-chat-form"
+          className="mt-s"
+        >
+          <Input
+            type="text"
+            label={t('New name')}
+            maxLength={100}
+            value={newName}
+            onChange={(e: React.ChangeEvent<HTMLInputElement>) => {
+              setNewName(e.target.value);
+            }}
+          />
+        </form>
+      </Box>
+    </Modal>
+  );
+};

src/frontend/apps/conversations/src/features/left-panel/components/__tests__/ConversationItemActions.test.tsx

@@ -0,0 +1,255 @@
+import { CunninghamProvider } from '@openfun/cunningham-react';
+import { render, screen, waitFor } from '@testing-library/react';
+import userEvent from '@testing-library/user-event';
+
+import { ToastProvider } from '@/components';
+import { ChatConversation } from '@/features/chat/types';
+
+import { ConversationItemActions } from '../ConversationItemActions';
+
+const mockPush = jest.fn();
+let mockPathname = '/';
+
+jest.mock('next/router', () => ({
+  useRouter: () => ({
+    push: mockPush,
+    pathname: mockPathname,
+    route: '/',
+    query: {},
+    asPath: '/',
+  }),
+}));
+
+jest.mock('next/navigation', () => ({
+  usePathname: () => mockPathname,
+}));
+
+jest.mock('react-i18next', () => ({
+  useTranslation: () => ({
+    t: (key: string, options?: Record<string, string>) => {
+      if (options) {
+        return Object.entries(options).reduce(
+          (acc, [k, v]) => acc.replace(`{{${k}}}`, v),
+          key,
+        );
+      }
+      return key;
+    },
+  }),
+}));
+
+jest.mock('i18next', () => ({
+  t: (key: string) => key,
+}));
+
+jest.mock('@/features/chat/api/useRenameConversation', () => ({
+  useRenameConversation: () => ({
+    mutate: jest.fn(),
+  }),
+}));
+
+jest.mock('@/features/chat/api/useRemoveConversation', () => ({
+  useRemoveConversation: () => ({
+    mutate: jest.fn(),
+  }),
+}));
+
+const renderWithProviders = (ui: React.ReactNode) => {
+  return render(
+    <CunninghamProvider>
+      <ToastProvider>{ui}</ToastProvider>
+    </CunninghamProvider>,
+  );
+};
+
+describe('ConversationItemActions', () => {
+  const mockConversation: ChatConversation = {
+    id: 'conv-123',
+    title: 'Original Title',
+    messages: [],
+    created_at: new Date().toISOString(),
+    updated_at: new Date().toISOString(),
+  };
+  beforeEach(() => {
+    jest.clearAllMocks();
+    mockPathname = '/';
+  });
+
+  const renderComponent = (conversation = mockConversation) => {
+    return renderWithProviders(
+      <ConversationItemActions conversation={conversation} />,
+    );
+  };
+
+  it('renders the actions button', () => {
+    renderComponent();
+
+    expect(
+      screen.getByTestId(
+        `conversation-item-actions-button-${mockConversation.id}`,
+      ),
+    ).toBeInTheDocument();
+  });
+
+  it('renders dropdown menu with correct aria-label', () => {
+    renderComponent();
+
+    expect(
+      screen.getByLabelText(
+        `Actions list for conversation ${mockConversation.title}`,
+      ),
+    ).toBeInTheDocument();
+  });
+
+  it('renders dropdown menu with fallback title when conversation has no title', () => {
+    const untitledConversation = { ...mockConversation, title: '' };
+    renderComponent(untitledConversation);
+
+    expect(
+      screen.getByLabelText(
+        `Actions list for conversation Untitled conversation`,
+      ),
+    ).toBeInTheDocument();
+  });
+
+  it('opens dropdown menu when clicking the actions button', async () => {
+    const user = userEvent.setup();
+    renderComponent();
+
+    const actionsButton = screen.getByLabelText(
+      `Actions list for conversation ${mockConversation.title}`,
+    );
+    await user.click(actionsButton);
+
+    expect(
+      screen.getByTestId(
+        `conversation-item-actions-rename-${mockConversation.id}`,
+      ),
+    ).toBeInTheDocument();
+    expect(
+      screen.getByTestId(
+        `conversation-item-actions-remove-${mockConversation.id}`,
+      ),
+    ).toBeInTheDocument();
+  });
+
+  it('displays rename and delete options in the dropdown', async () => {
+    const user = userEvent.setup();
+    renderComponent();
+
+    const actionsButton = screen.getByLabelText(
+      `Actions list for conversation ${mockConversation.title}`,
+    );
+    await user.click(actionsButton);
+
+    expect(screen.getByText('Rename chat')).toBeInTheDocument();
+    expect(screen.getByText('Delete chat')).toBeInTheDocument();
+  });
+
+  it('opens rename modal when clicking rename option', async () => {
+    const user = userEvent.setup();
+    renderComponent();
+
+    const actionsButton = screen.getByLabelText(
+      `Actions list for conversation ${mockConversation.title}`,
+    );
+    await user.click(actionsButton);
+
+    const renameOption = screen.getByTestId(
+      `conversation-item-actions-rename-${mockConversation.id}`,
+    );
+    await user.click(renameOption);
+    // Modal should be open
+    await waitFor(() => {
+      expect(screen.getByRole('dialog')).toBeInTheDocument();
+    });
+
+    expect(screen.getByRole('textbox')).toHaveValue(mockConversation.title);
+
+    expect(screen.getByTestId('rename-chat-form')).toBeInTheDocument();
+  });
+
+  it('opens delete modal when clicking delete option', async () => {
+    const user = userEvent.setup();
+    renderComponent();
+
+    const actionsButton = screen.getByLabelText(
+      `Actions list for conversation ${mockConversation.title}`,
+    );
+    await user.click(actionsButton);
+
+    const deleteOption = screen.getByTestId(
+      `conversation-item-actions-remove-${mockConversation.id}`,
+    );
+    await user.click(deleteOption);
+
+    await waitFor(() => {
+      expect(screen.getByRole('dialog')).toBeInTheDocument();
+    });
+    expect(screen.getByTestId('delete-chat-confirm')).toBeInTheDocument();
+  });
+
+  it('does not render modals initially', () => {
+    renderComponent();
+
+    expect(screen.queryByRole('dialog')).not.toBeInTheDocument();
+    expect(screen.queryByTestId('delete-chat-confirm')).not.toBeInTheDocument();
+    expect(screen.queryByTestId('rename-chat-form')).not.toBeInTheDocument();
+  });
+
+  it('closes rename modal when onClose is called', async () => {
+    const user = userEvent.setup();
+    renderComponent();
+
+    // Open dropdown and click rename
+    const actionsButton = screen.getByLabelText(
+      `Actions list for conversation ${mockConversation.title}`,
+    );
+    await user.click(actionsButton);
+    await user.click(
+      screen.getByTestId(
+        `conversation-item-actions-rename-${mockConversation.id}`,
+      ),
+    );
+
+    // Modal should be open
+    await waitFor(() => {
+      expect(screen.getByRole('dialog')).toBeInTheDocument();
+    });
+
+    // Close the modal
+    await user.click(screen.getByText('Cancel'));
+
+    await waitFor(() => {
+      expect(screen.queryByRole('dialog')).not.toBeInTheDocument();
+    });
+  });
+
+  it('closes delete modal when onClose is called', async () => {
+    const user = userEvent.setup();
+    renderComponent();
+
+    // Open dropdown and click delete
+    const actionsButton = screen.getByLabelText(
+      `Actions list for conversation ${mockConversation.title}`,
+    );
+    await user.click(actionsButton);
+    await user.click(
+      screen.getByTestId(
+        `conversation-item-actions-remove-${mockConversation.id}`,
+      ),
+    );
+
+    // Modal should be open
+    await waitFor(() => {
+      expect(screen.getByRole('dialog')).toBeInTheDocument();
+    });
+
+    // Close the modal
+    await user.click(screen.getByText('Cancel'));
+
+    await waitFor(() => {
+      expect(screen.queryByRole('dialog')).not.toBeInTheDocument();
+    });
+  });
+});

src/frontend/apps/conversations/src/features/left-panel/components/__tests__/ModalRenameConversation.test.tsx

@@ -0,0 +1,280 @@
+import { CunninghamProvider } from '@openfun/cunningham-react';
+import { render, screen, waitFor } from '@testing-library/react';
+import userEvent from '@testing-library/user-event';
+
+import { useToast } from '@/components';
+import { useRenameConversation } from '@/features/chat/api/useRenameConversation';
+import { ChatConversation } from '@/features/chat/types';
+
+import { ModalRenameConversation } from '../ModalRenameConversation';
+
+jest.mock('@/components', () => ({
+  ...jest.requireActual('@/components'),
+  useToast: jest.fn(),
+}));
+
+jest.mock('@/features/chat/api/useRenameConversation');
+
+jest.mock('react-i18next', () => ({
+  useTranslation: () => ({
+    t: (key: string, options?: Record<string, string>) => {
+      if (options) {
+        return Object.entries(options).reduce(
+          (acc, [k, v]) => acc.replace(`{{${k}}}`, v),
+          key,
+        );
+      }
+      return key;
+    },
+  }),
+}));
+jest.mock('i18next', () => ({
+  t: (key: string) => key,
+}));
+const renderWithProviders = (component: React.ReactNode) => {
+  return render(<CunninghamProvider>{component}</CunninghamProvider>);
+};
+
+describe('ModalRenameConversation', () => {
+  const mockOnClose = jest.fn();
+  const mockShowToast = jest.fn();
+  const mockRenameConversation = jest.fn();
+
+  const mockConversation: ChatConversation = {
+    id: 'conv-123',
+    title: 'Original Title',
+    messages: [],
+    created_at: new Date().toISOString(),
+    updated_at: new Date().toISOString(),
+  } as ChatConversation;
+
+  beforeEach(() => {
+    jest.clearAllMocks();
+    (useToast as jest.Mock).mockReturnValue({
+      showToast: mockShowToast,
+    });
+    (useRenameConversation as jest.Mock).mockReturnValue({
+      mutate: mockRenameConversation,
+    });
+  });
+
+  it('renders the modal with correct title and initial value', () => {
+    renderWithProviders(
+      <ModalRenameConversation
+        onClose={mockOnClose}
+        conversation={mockConversation}
+      />,
+    );
+
+    expect(screen.getByText('Rename chat')).toBeInTheDocument();
+    expect(screen.getByRole('textbox')).toHaveValue('Original Title');
+    expect(screen.getByText('Cancel')).toBeInTheDocument();
+    expect(screen.getByText('Rename')).toBeInTheDocument();
+  });
+
+  it('updates input value when user types', async () => {
+    const user = userEvent.setup();
+    renderWithProviders(
+      <ModalRenameConversation
+        onClose={mockOnClose}
+        conversation={mockConversation}
+      />,
+    );
+
+    const input = screen.getByRole('textbox');
+
+    await user.clear(input);
+    await user.type(input, 'New Title');
+
+    expect(input).toHaveValue('New Title');
+  });
+
+  it('closes modal when Cancel button is clicked', async () => {
+    const user = userEvent.setup();
+    renderWithProviders(
+      <ModalRenameConversation
+        onClose={mockOnClose}
+        conversation={mockConversation}
+      />,
+    );
+
+    await user.click(screen.getByText('Cancel'));
+
+    expect(mockOnClose).toHaveBeenCalledTimes(1);
+  });
+
+  it('submits form with new name and shows success toast', async () => {
+    const user = userEvent.setup();
+    let onSuccessCallback: (() => void) | undefined;
+
+    (useRenameConversation as jest.Mock).mockImplementation(({ onSuccess }) => {
+      onSuccessCallback = onSuccess;
+      return { mutate: mockRenameConversation };
+    });
+
+    renderWithProviders(
+      <ModalRenameConversation
+        onClose={mockOnClose}
+        conversation={mockConversation}
+      />,
+    );
+
+    const input = screen.getByRole('textbox');
+    await user.clear(input);
+    await user.type(input, 'Updated Title');
+    await user.click(screen.getByText('Rename'));
+
+    expect(mockRenameConversation).toHaveBeenCalledWith({
+      conversationId: 'conv-123',
+      title: 'Updated Title',
+    });
+
+    onSuccessCallback?.();
+
+    await waitFor(() => {
+      expect(mockShowToast).toHaveBeenCalledWith(
+        'success',
+        'The conversation has been renamed.',
+        undefined,
+        4000,
+      );
+    });
+    expect(mockOnClose).toHaveBeenCalled();
+  });
+
+  it('does not submit form when new name is empty or whitespace', async () => {
+    const user = userEvent.setup();
+    renderWithProviders(
+      <ModalRenameConversation
+        onClose={mockOnClose}
+        conversation={mockConversation}
+      />,
+    );
+
+    const input = screen.getByRole('textbox');
+    await user.clear(input);
+    await user.type(input, '   ');
+    await user.click(screen.getByText('Rename'));
+
+    expect(mockRenameConversation).not.toHaveBeenCalled();
+  });
+
+  it('shows error toast when rename fails with cause', async () => {
+    const user = userEvent.setup();
+    let onErrorCallback: ((error: any) => void) | undefined;
+
+    (useRenameConversation as jest.Mock).mockImplementation(({ onError }) => {
+      onErrorCallback = onError;
+      return { mutate: mockRenameConversation };
+    });
+
+    renderWithProviders(
+      <ModalRenameConversation
+        onClose={mockOnClose}
+        conversation={mockConversation}
+      />,
+    );
+
+    const input = screen.getByRole('textbox');
+    await user.clear(input);
+    await user.type(input, 'New Title');
+    await user.click(screen.getByText('Rename'));
+
+    const error = {
+      cause: ['Specific error from API'],
+      message: 'Generic error',
+    };
+    onErrorCallback?.(error);
+
+    await waitFor(() => {
+      expect(mockShowToast).toHaveBeenCalledWith(
+        'error',
+        'Specific error from API',
+        undefined,
+        4000,
+      );
+    });
+  });
+
+  it('shows error toast with message when no cause is provided', async () => {
+    const user = userEvent.setup();
+    let onErrorCallback: ((error: any) => void) | undefined;
+
+    (useRenameConversation as jest.Mock).mockImplementation(({ onError }) => {
+      onErrorCallback = onError;
+      return { mutate: mockRenameConversation };
+    });
+
+    renderWithProviders(
+      <ModalRenameConversation
+        onClose={mockOnClose}
+        conversation={mockConversation}
+      />,
+    );
+
+    const input = screen.getByRole('textbox');
+    await user.clear(input);
+    await user.type(input, 'New Title');
+    await user.click(screen.getByText('Rename'));
+
+    const error = {
+      message: 'Network error',
+    };
+    onErrorCallback?.(error);
+
+    await waitFor(() => {
+      expect(mockShowToast).toHaveBeenCalledWith(
+        'error',
+        'Network error',
+        undefined,
+        4000,
+      );
+    });
+  });
+
+  it('shows default error message when error has no cause or message', async () => {
+    const user = userEvent.setup();
+    let onErrorCallback: ((error: any) => void) | undefined;
+
+    (useRenameConversation as jest.Mock).mockImplementation(({ onError }) => {
+      onErrorCallback = onError;
+      return { mutate: mockRenameConversation };
+    });
+
+    renderWithProviders(
+      <ModalRenameConversation
+        onClose={mockOnClose}
+        conversation={mockConversation}
+      />,
+    );
+
+    const input = screen.getByRole('textbox');
+    await user.clear(input);
+    await user.type(input, 'New Title');
+    await user.click(screen.getByText('Rename'));
+
+    const error = {};
+    onErrorCallback?.(error);
+
+    await waitFor(() => {
+      expect(mockShowToast).toHaveBeenCalledWith(
+        'error',
+        'An error occurred while renaming the conversation',
+        undefined,
+        4000,
+      );
+    });
+  });
+
+  it('enforces maxLength of 100 characters on input', () => {
+    renderWithProviders(
+      <ModalRenameConversation
+        onClose={mockOnClose}
+        conversation={mockConversation}
+      />,
+    );
+
+    const input = screen.getByRole('textbox');
+    expect(input).toHaveAttribute('maxLength', '100');
+  });
+});

src/frontend/apps/conversations/src/i18n/translations.json

@@ -88,6 +88,7 @@
       "Quick search input": "Saisie de recherche rapide",
       "Remove attachment": "Supprimer la pièce jointe",
       "Research on the web": "Rechercher sur le web",
+      "Retry": "Réessayer",
       "Search": "Rechercher",
       "Search for a chat": "Rechercher un chat",
       "Search results": "Résultats de la recherche",
@@ -100,7 +101,7 @@
       "Simple chat icon": "Icône de chat simple",
       "Something bad happens, please retry.": "Une erreur inattendue s'est produite, veuillez réessayer.",
       "Sorry, an error occurred. Please try again.": "Désolé, une erreur s'est produite. Veuillez réessayer.",
-      "Start a new conversation.": "Commencer une nouvelle conversation.",
+      "Start a new conversation": "Commencer une nouvelle conversation",
       "Start conversation": "Entamer la conversation",
       "Stop": "Stop",
       "Summarizing...": "Résumé en cours...",
@@ -220,6 +221,7 @@
       "Quick search input": "Snelle zoekinvoer",
       "Remove attachment": "Bijlage verwijderen",
       "Research on the web": "Onderzoek op het internet",
+      "Retry": "Opnieuw proberen",
       "Search": "Zoek",
       "Search for a chat": "Zoek naar een chat",
       "Search results": "Zoekresultaten",
@@ -232,7 +234,7 @@
       "Simple chat icon": "Eenvoudig chatpictogram",
       "Something bad happens, please retry.": "Er is iets misgegaan. Probeer het opnieuw.",
       "Sorry, an error occurred. Please try again.": "Sorry, er is een fout opgetreden. Probeer het opnieuw.",
-      "Start a new conversation.": "Begin een nieuw gesprek.",
+      "Start a new conversation": "Begin een nieuw gesprek",
       "Start conversation": "Begin een gesprek",
       "Stop": "Stop",
       "Summarizing...": "Samenvatten...",
@@ -352,6 +354,7 @@
       "Quick search input": "Быстрый поиск",
       "Remove attachment": "Удалить вложение",
       "Research on the web": "Исследование в Интернете",
+      "Retry": "Повторить",
       "Search": "Поиск",
       "Search for a chat": "Поиск беседы",
       "Search results": "Результаты поиска",
@@ -364,7 +367,7 @@
       "Simple chat icon": "Простой значок чата",
       "Something bad happens, please retry.": "Что-то пошло не так, повторите попытку.",
       "Sorry, an error occurred. Please try again.": "Извините, произошла ошибка. Пожалуйста, попробуйте ещё раз.",
-      "Start a new conversation.": "Начать новую беседу.",
+      "Start a new conversation": "Начать новую беседу",
       "Start conversation": "Начать беседу",
       "Stop": "Остановить",
       "Summarizing...": "Обобщение...",
@@ -484,6 +487,7 @@
       "Quick search input": "Швидкий пошук",
       "Remove attachment": "Видалити вкладення",
       "Research on the web": "Дослідження в Інтернеті",
+      "Retry": "Повторити",
       "Search": "Пошук",
       "Search for a chat": "Пошук розмови",
       "Search results": "Результати пошуку",
@@ -496,7 +500,7 @@
       "Simple chat icon": "Проста піктограма розмови",
       "Something bad happens, please retry.": "Сталася помилка, спробуйте ще раз.",
       "Sorry, an error occurred. Please try again.": "Вибачте, виникла помилка. Спробуйте ще раз.",
-      "Start a new conversation.": "Розпочати нову розмову.",
+      "Start a new conversation": "Розпочати нову розмову",
       "Start conversation": "Почати розмову",
       "Stop": "Зупинити",
       "Summarizing...": "Узагальнення...",

src/frontend/apps/e2e/__tests__/app-conversations/chat.spec.ts

@@ -52,7 +52,7 @@ test.describe('Chat page', () => {
 
     const messageContent = page.getByTestId('assistant-message-content');
     await expect(messageContent).toBeVisible();
-    await expect(messageContent).not.toBeEmpty(); 
+    await expect(messageContent).not.toBeEmpty();
 
     // Check history
     const chatHistoryLink = page

src/frontend/apps/e2e/package.json

@@ -1,6 +1,6 @@
 {
   "name": "app-e2e",
-  "version": "0.0.10",
+  "version": "0.0.11",
   "private": true,
   "scripts": {
     "lint": "eslint . --ext .ts",

src/frontend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "conversations",
-  "version": "0.0.10",
+  "version": "0.0.11",
   "private": true,
   "workspaces": {
     "packages": [

src/frontend/packages/eslint-config-conversations/package.json

@@ -1,6 +1,6 @@
 {
   "name": "eslint-config-conversations",
-  "version": "0.0.10",
+  "version": "0.0.11",
   "license": "MIT",
   "scripts": {
     "lint": "eslint --ext .js ."

src/frontend/packages/i18n/package.json

@@ -1,6 +1,6 @@
 {
   "name": "packages-i18n",
-  "version": "0.0.10",
+  "version": "0.0.11",
   "private": true,
   "scripts": {
     "extract-translation": "yarn extract-translation:conversations",

src/frontend/yarn.lock

@@ -11355,9 +11355,9 @@ posthog-js@1.249.3:
     web-vitals "^4.2.4"
 
 preact@^10.19.3:
-  version "10.26.6"
-  resolved "https://registry.npmjs.org/preact/-/preact-10.26.6.tgz"
-  integrity sha512-5SRRBinwpwkaD+OqlBDeITlRgvd8I8QlxHJw9AxSdMNV6O+LodN9nUyYGpSF7sadHjs6RzeFShMexC6DbtWr9g==
+  version "10.24.0"
+  resolved "https://registry.npmjs.org/preact/-/preact-10.24.0.tgz"
+  integrity sha512-aK8Cf+jkfyuZ0ZZRG9FbYqwmEiGQ4y/PUO4SuTWoyWL244nZZh7bd5h2APd4rSNDYTBNghg1L+5iJN3Skxtbsw==
 
 prelude-ls@^1.2.1:
   version "1.2.1"

src/mail/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mail_mjml",
-  "version": "0.0.10",
+  "version": "0.0.11",
   "description": "An util to generate html and text django's templates from mjml templates",
   "type": "module",
   "dependencies": {

src/mail/yarn.lock

@@ -399,10 +399,10 @@ glob-parent@~5.1.2:
   dependencies:
     is-glob "^4.0.1"
 
-glob@^10.3.10, glob@^10.3.3:
-  version "10.4.5"
-  resolved "https://registry.yarnpkg.com/glob/-/glob-10.4.5.tgz#f4d9f0b90ffdbab09c9d77f5f29b4262517b0956"
-  integrity sha512-7Bv8RF0k6xjo7d4A/PxYLbUCfb6c+Vpd2/mB2yRDlew7Jb5hEXiCD9ibfO7wpk8i4sevK6DFny9h7EYbM3/sHg==
+glob@^10.5.0:
+  version "10.5.0"
+  resolved "https://registry.yarnpkg.com/glob/-/glob-10.5.0.tgz#8ec0355919cd3338c28428a23d4f24ecc5fe738c"
+  integrity sha512-DfXN8DfhJ7NH3Oe7cFmu3NCu1wKbkReJ8TorzSAFbSKrlNaQSKfIzqYqVY8zlbs2NLBbWpRiU52GX2PbaBVNkg==
   dependencies:
     foreground-child "^3.1.0"
     jackspeak "^3.1.2"